/*
 *  fs/nfs/nfs4proc.c
 *
 *  Client-side procedure declarations for NFSv4.
 *
 *  Copyright (c) 2002 The Regents of the University of Michigan.
 *  All rights reserved.
 *
 *  Kendrick Smith <kmsmith@umich.edu>
 *  Andy Adamson   <andros@umich.edu>
 *
 *  Redistribution and use in source and binary forms, with or without
 *  modification, are permitted provided that the following conditions
 *  are met:
 *
 *  1. Redistributions of source code must retain the above copyright
 *     notice, this list of conditions and the following disclaimer.
 *  2. Redistributions in binary form must reproduce the above copyright
 *     notice, this list of conditions and the following disclaimer in the
 *     documentation and/or other materials provided with the distribution.
 *  3. Neither the name of the University nor the names of its
 *     contributors may be used to endorse or promote products derived
 *     from this software without specific prior written permission.
 *
 *  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
 *  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
 *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
 *  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
 *  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
 *  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
 *  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
 *  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
 *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
 *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
 *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */

#include <linux/mm.h>
#include <linux/delay.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/ratelimit.h>
#include <linux/printk.h>
#include <linux/slab.h>
#include <linux/sunrpc/clnt.h>
#include <linux/nfs.h>
#include <linux/nfs4.h>
#include <linux/nfs_fs.h>
#include <linux/nfs_page.h>
#include <linux/nfs_mount.h>
#include <linux/namei.h>
#include <linux/mount.h>
#include <linux/module.h>
#include <linux/nfs_idmap.h>
#include <linux/xattr.h>
#include <linux/utsname.h>
#include <linux/freezer.h>

#include "nfs4_fs.h"
#include "delegation.h"
#include "internal.h"
#include "iostat.h"
#include "callback.h"
#include "pnfs.h"
#include "netns.h"
#include "nfs4session.h"
#include "fscache.h"

#include "nfs4trace.h"

#define NFSDBG_FACILITY         NFSDBG_PROC

#define NFS4_POLL_RETRY_MIN     (HZ/10)
#define NFS4_POLL_RETRY_MAX     (15*HZ)

struct nfs4_opendata;
static int _nfs4_proc_open(struct nfs4_opendata *data);
static int _nfs4_recover_proc_open(struct nfs4_opendata *data);
static int nfs4_do_fsinfo(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *);
static int nfs4_async_handle_error(struct rpc_task *, const struct nfs_server *, struct nfs4_state *, long *);
static void nfs_fixup_referral_attributes(struct nfs_fattr *fattr);
static int nfs4_proc_getattr(struct nfs_server *, struct nfs_fh *, struct nfs_fattr *, struct nfs4_label *label);
static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fattr *fattr, struct nfs4_label *label);
static int nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
                            struct nfs_fattr *fattr, struct iattr *sattr,
                            struct nfs4_state *state, struct nfs4_label *ilabel,
                            struct nfs4_label *olabel);
#ifdef CONFIG_NFS_V4_1
static int nfs41_test_stateid(struct nfs_server *, nfs4_stateid *,
                struct rpc_cred *);
static int nfs41_free_stateid(struct nfs_server *, nfs4_stateid *,
                struct rpc_cred *);
#endif

#ifdef CONFIG_NFS_V4_SECURITY_LABEL
static inline struct nfs4_label *
nfs4_label_init_security(struct inode *dir, struct dentry *dentry,
        struct iattr *sattr, struct nfs4_label *label)
{
        int err;

        if (label == NULL)
                return NULL;

        if (nfs_server_capable(dir, NFS_CAP_SECURITY_LABEL) == 0)
                return NULL;

        err = security_dentry_init_security(dentry, sattr->ia_mode,
                                &dentry->d_name, (void **)&label->label, &label->len);
        if (err == 0)
                return label;

        return NULL;
}
static inline void
nfs4_label_release_security(struct nfs4_label *label)
{
        if (label)
                security_release_secctx(label->label, label->len);
}
static inline u32 *nfs4_bitmask(struct nfs_server *server, struct nfs4_label *label)
{
        if (label)
                return server->attr_bitmask;

        return server->attr_bitmask_nl;
}
#else
static inline struct nfs4_label *
nfs4_label_init_security(struct inode *dir, struct dentry *dentry,
        struct iattr *sattr, struct nfs4_label *l)
{ return NULL; }
static inline void
nfs4_label_release_security(struct nfs4_label *label)
{ return; }
static inline u32 *
nfs4_bitmask(struct nfs_server *server, struct nfs4_label *label)
{ return server->attr_bitmask; }
#endif

/* Prevent leaks of NFSv4 errors into userland */
static int nfs4_map_errors(int err)
{
        if (err >= -1000)
                return err;
        switch (err) {
        case -NFS4ERR_RESOURCE:
        case -NFS4ERR_LAYOUTTRYLATER:
        case -NFS4ERR_RECALLCONFLICT:
                return -EREMOTEIO;
        case -NFS4ERR_WRONGSEC:
        case -NFS4ERR_WRONG_CRED:
                return -EPERM;
        case -NFS4ERR_BADOWNER:
        case -NFS4ERR_BADNAME:
                return -EINVAL;
        case -NFS4ERR_SHARE_DENIED:
                return -EACCES;
        case -NFS4ERR_MINOR_VERS_MISMATCH:
                return -EPROTONOSUPPORT;
        case -NFS4ERR_FILE_OPEN:
                return -EBUSY;
        default:
                dprintk("%s could not handle NFSv4 error %d\n",
                                __func__, -err);
                break;
        }
        return -EIO;
}

/*
 * This is our standard bitmap for GETATTR requests.
 */
const u32 nfs4_fattr_bitmap[3] = {
        FATTR4_WORD0_TYPE
        | FATTR4_WORD0_CHANGE
        | FATTR4_WORD0_SIZE
        | FATTR4_WORD0_FSID
        | FATTR4_WORD0_FILEID,
        FATTR4_WORD1_MODE
        | FATTR4_WORD1_NUMLINKS
        | FATTR4_WORD1_OWNER
        | FATTR4_WORD1_OWNER_GROUP
        | FATTR4_WORD1_RAWDEV
        | FATTR4_WORD1_SPACE_USED
        | FATTR4_WORD1_TIME_ACCESS
        | FATTR4_WORD1_TIME_METADATA
        | FATTR4_WORD1_TIME_MODIFY,
#ifdef CONFIG_NFS_V4_SECURITY_LABEL
        FATTR4_WORD2_SECURITY_LABEL
#endif
};

static const u32 nfs4_pnfs_open_bitmap[3] = {
        FATTR4_WORD0_TYPE
        | FATTR4_WORD0_CHANGE
        | FATTR4_WORD0_SIZE
        | FATTR4_WORD0_FSID
        | FATTR4_WORD0_FILEID,
        FATTR4_WORD1_MODE
        | FATTR4_WORD1_NUMLINKS
        | FATTR4_WORD1_OWNER
        | FATTR4_WORD1_OWNER_GROUP
        | FATTR4_WORD1_RAWDEV
        | FATTR4_WORD1_SPACE_USED
        | FATTR4_WORD1_TIME_ACCESS
        | FATTR4_WORD1_TIME_METADATA
        | FATTR4_WORD1_TIME_MODIFY,
        FATTR4_WORD2_MDSTHRESHOLD
};

static const u32 nfs4_open_noattr_bitmap[3] = {
        FATTR4_WORD0_TYPE
        | FATTR4_WORD0_CHANGE
        | FATTR4_WORD0_FILEID,
};

const u32 nfs4_statfs_bitmap[3] = {
        FATTR4_WORD0_FILES_AVAIL
        | FATTR4_WORD0_FILES_FREE
        | FATTR4_WORD0_FILES_TOTAL,
        FATTR4_WORD1_SPACE_AVAIL
        | FATTR4_WORD1_SPACE_FREE
        | FATTR4_WORD1_SPACE_TOTAL
};

const u32 nfs4_pathconf_bitmap[3] = {
        FATTR4_WORD0_MAXLINK
        | FATTR4_WORD0_MAXNAME,
        0
};

const u32 nfs4_fsinfo_bitmap[3] = { FATTR4_WORD0_MAXFILESIZE
                        | FATTR4_WORD0_MAXREAD
                        | FATTR4_WORD0_MAXWRITE
                        | FATTR4_WORD0_LEASE_TIME,
                        FATTR4_WORD1_TIME_DELTA
                        | FATTR4_WORD1_FS_LAYOUT_TYPES,
                        FATTR4_WORD2_LAYOUT_BLKSIZE
};

const u32 nfs4_fs_locations_bitmap[3] = {
        FATTR4_WORD0_TYPE
        | FATTR4_WORD0_CHANGE
        | FATTR4_WORD0_SIZE
        | FATTR4_WORD0_FSID
        | FATTR4_WORD0_FILEID
        | FATTR4_WORD0_FS_LOCATIONS,
        FATTR4_WORD1_MODE
        | FATTR4_WORD1_NUMLINKS
        | FATTR4_WORD1_OWNER
        | FATTR4_WORD1_OWNER_GROUP
        | FATTR4_WORD1_RAWDEV
        | FATTR4_WORD1_SPACE_USED
        | FATTR4_WORD1_TIME_ACCESS
        | FATTR4_WORD1_TIME_METADATA
        | FATTR4_WORD1_TIME_MODIFY
        | FATTR4_WORD1_MOUNTED_ON_FILEID,
};

static void nfs4_setup_readdir(u64 cookie, __be32 *verifier, struct dentry *dentry,
                struct nfs4_readdir_arg *readdir)
{
        __be32 *start, *p;

        if (cookie > 2) {
                readdir->cookie = cookie;
                memcpy(&readdir->verifier, verifier, sizeof(readdir->verifier));
                return;
        }

        readdir->cookie = 0;
        memset(&readdir->verifier, 0, sizeof(readdir->verifier));
        if (cookie == 2)
                return;
        
        /*
         * NFSv4 servers do not return entries for '.' and '..'
         * Therefore, we fake these entries here.  We let '.'
         * have cookie 0 and '..' have cookie 1.  Note that
         * when talking to the server, we always send cookie 0
         * instead of 1 or 2.
         */
        start = p = kmap_atomic(*readdir->pages);
        
        if (cookie == 0) {
                *p++ = xdr_one;                                  /* next */
                *p++ = xdr_zero;                   /* cookie, first word */
                *p++ = xdr_one;                   /* cookie, second word */
                *p++ = xdr_one;                             /* entry len */
                memcpy(p, ".\0\0\0", 4);                        /* entry */
                p++;
                *p++ = xdr_one;                         /* bitmap length */
                *p++ = htonl(FATTR4_WORD0_FILEID);             /* bitmap */
                *p++ = htonl(8);              /* attribute buffer length */
                p = xdr_encode_hyper(p, NFS_FILEID(dentry->d_inode));
        }
        
        *p++ = xdr_one;                                  /* next */
        *p++ = xdr_zero;                   /* cookie, first word */
        *p++ = xdr_two;                   /* cookie, second word */
        *p++ = xdr_two;                             /* entry len */
        memcpy(p, "..\0\0", 4);                         /* entry */
        p++;
        *p++ = xdr_one;                         /* bitmap length */
        *p++ = htonl(FATTR4_WORD0_FILEID);             /* bitmap */
        *p++ = htonl(8);              /* attribute buffer length */
        p = xdr_encode_hyper(p, NFS_FILEID(dentry->d_parent->d_inode));

        readdir->pgbase = (char *)p - (char *)start;
        readdir->count -= readdir->pgbase;
        kunmap_atomic(start);
}

static long nfs4_update_delay(long *timeout)
{
        long ret;
        if (!timeout)
                return NFS4_POLL_RETRY_MAX;
        if (*timeout <= 0)
                *timeout = NFS4_POLL_RETRY_MIN;
        if (*timeout > NFS4_POLL_RETRY_MAX)
                *timeout = NFS4_POLL_RETRY_MAX;
        ret = *timeout;
        *timeout <<= 1;
        return ret;
}

static int nfs4_delay(struct rpc_clnt *clnt, long *timeout)
{
        int res = 0;

        might_sleep();

        freezable_schedule_timeout_killable_unsafe(
                nfs4_update_delay(timeout));
        if (fatal_signal_pending(current))
                res = -ERESTARTSYS;
        return res;
}

/* This is the error handling routine for processes that are allowed
 * to sleep.
 */
int nfs4_handle_exception(struct nfs_server *server, int errorcode, struct nfs4_exception *exception)
{
        struct nfs_client *clp = server->nfs_client;
        struct nfs4_state *state = exception->state;
        struct inode *inode = exception->inode;
        int ret = errorcode;

        exception->retry = 0;
        switch(errorcode) {
                case 0:
                        return 0;
                case -NFS4ERR_OPENMODE:
                        if (inode && nfs4_have_delegation(inode, FMODE_READ)) {
                                nfs4_inode_return_delegation(inode);
                                exception->retry = 1;
                                return 0;
                        }
                        if (state == NULL)
                                break;
                        ret = nfs4_schedule_stateid_recovery(server, state);
                        if (ret < 0)
                                break;
                        goto wait_on_recovery;
                case -NFS4ERR_DELEG_REVOKED:
                case -NFS4ERR_ADMIN_REVOKED:
                case -NFS4ERR_BAD_STATEID:
                        if (state == NULL)
                                break;
                        ret = nfs4_schedule_stateid_recovery(server, state);
                        if (ret < 0)
                                break;
                        goto wait_on_recovery;
                case -NFS4ERR_EXPIRED:
                        if (state != NULL) {
                                ret = nfs4_schedule_stateid_recovery(server, state);
                                if (ret < 0)
                                        break;
                        }
                case -NFS4ERR_STALE_STATEID:
                case -NFS4ERR_STALE_CLIENTID:
                        nfs4_schedule_lease_recovery(clp);
                        goto wait_on_recovery;
                case -NFS4ERR_MOVED:
                        ret = nfs4_schedule_migration_recovery(server);
                        if (ret < 0)
                                break;
                        goto wait_on_recovery;
                case -NFS4ERR_LEASE_MOVED:
                        nfs4_schedule_lease_moved_recovery(clp);
                        goto wait_on_recovery;
#if defined(CONFIG_NFS_V4_1)
                case -NFS4ERR_BADSESSION:
                case -NFS4ERR_BADSLOT:
                case -NFS4ERR_BAD_HIGH_SLOT:
                case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
                case -NFS4ERR_DEADSESSION:
                case -NFS4ERR_SEQ_FALSE_RETRY:
                case -NFS4ERR_SEQ_MISORDERED:
                        dprintk("%s ERROR: %d Reset session\n", __func__,
                                errorcode);
                        nfs4_schedule_session_recovery(clp->cl_session, errorcode);
                        goto wait_on_recovery;
#endif /* defined(CONFIG_NFS_V4_1) */
                case -NFS4ERR_FILE_OPEN:
                        if (exception->timeout > HZ) {
                                /* We have retried a decent amount, time to
                                 * fail
                                 */
                                ret = -EBUSY;
                                break;
                        }
                case -NFS4ERR_GRACE:
                case -NFS4ERR_DELAY:
                        ret = nfs4_delay(server->client, &exception->timeout);
                        if (ret != 0)
                                break;
                case -NFS4ERR_RETRY_UNCACHED_REP:
                case -NFS4ERR_OLD_STATEID:
                        exception->retry = 1;
                        break;
                case -NFS4ERR_BADOWNER:
                        /* The following works around a Linux server bug! */
                case -NFS4ERR_BADNAME:
                        if (server->caps & NFS_CAP_UIDGID_NOMAP) {
                                server->caps &= ~NFS_CAP_UIDGID_NOMAP;
                                exception->retry = 1;
                                printk(KERN_WARNING "NFS: v4 server %s "
                                                "does not accept raw "
                                                "uid/gids. "
                                                "Reenabling the idmapper.\n",
                                                server->nfs_client->cl_hostname);
                        }
        }
        /* We failed to handle the error */
        return nfs4_map_errors(ret);
wait_on_recovery:
        ret = nfs4_wait_clnt_recover(clp);
        if (test_bit(NFS_MIG_FAILED, &server->mig_status))
                return -EIO;
        if (ret == 0)
                exception->retry = 1;
        return ret;
}

/*
 * Return 'true' if 'clp' is using an rpc_client that is integrity protected
 * or 'false' otherwise.
 */
static bool _nfs4_is_integrity_protected(struct nfs_client *clp)
{
        rpc_authflavor_t flavor = clp->cl_rpcclient->cl_auth->au_flavor;

        if (flavor == RPC_AUTH_GSS_KRB5I ||
            flavor == RPC_AUTH_GSS_KRB5P)
                return true;

        return false;
}

static void do_renew_lease(struct nfs_client *clp, unsigned long timestamp)
{
        spin_lock(&clp->cl_lock);
        if (time_before(clp->cl_last_renewal,timestamp))
                clp->cl_last_renewal = timestamp;
        spin_unlock(&clp->cl_lock);
}

static void renew_lease(const struct nfs_server *server, unsigned long timestamp)
{
        do_renew_lease(server->nfs_client, timestamp);
}

struct nfs4_call_sync_data {
        const struct nfs_server *seq_server;
        struct nfs4_sequence_args *seq_args;
        struct nfs4_sequence_res *seq_res;
};

static void nfs4_init_sequence(struct nfs4_sequence_args *args,
                               struct nfs4_sequence_res *res, int cache_reply)
{
        args->sa_slot = NULL;
        args->sa_cache_this = cache_reply;
        args->sa_privileged = 0;

        res->sr_slot = NULL;
}

static void nfs4_set_sequence_privileged(struct nfs4_sequence_args *args)
{
        args->sa_privileged = 1;
}

static int nfs40_setup_sequence(const struct nfs_server *server,
                                struct nfs4_sequence_args *args,
                                struct nfs4_sequence_res *res,
                                struct rpc_task *task)
{
        struct nfs4_slot_table *tbl = server->nfs_client->cl_slot_tbl;
        struct nfs4_slot *slot;

        /* slot already allocated? */
        if (res->sr_slot != NULL)
                goto out_start;

        spin_lock(&tbl->slot_tbl_lock);
        if (nfs4_slot_tbl_draining(tbl) && !args->sa_privileged)
                goto out_sleep;

        slot = nfs4_alloc_slot(tbl);
        if (IS_ERR(slot)) {
                if (slot == ERR_PTR(-ENOMEM))
                        task->tk_timeout = HZ >> 2;
                goto out_sleep;
        }
        spin_unlock(&tbl->slot_tbl_lock);

        args->sa_slot = slot;
        res->sr_slot = slot;

out_start:
        rpc_call_start(task);
        return 0;

out_sleep:
        if (args->sa_privileged)
                rpc_sleep_on_priority(&tbl->slot_tbl_waitq, task,
                                NULL, RPC_PRIORITY_PRIVILEGED);
        else
                rpc_sleep_on(&tbl->slot_tbl_waitq, task, NULL);
        spin_unlock(&tbl->slot_tbl_lock);
        return -EAGAIN;
}

static int nfs40_sequence_done(struct rpc_task *task,
                               struct nfs4_sequence_res *res)
{
        struct nfs4_slot *slot = res->sr_slot;
        struct nfs4_slot_table *tbl;

        if (slot == NULL)
                goto out;

        tbl = slot->table;
        spin_lock(&tbl->slot_tbl_lock);
        if (!nfs41_wake_and_assign_slot(tbl, slot))
                nfs4_free_slot(tbl, slot);
        spin_unlock(&tbl->slot_tbl_lock);

        res->sr_slot = NULL;
out:
        return 1;
}

#if defined(CONFIG_NFS_V4_1)

static void nfs41_sequence_free_slot(struct nfs4_sequence_res *res)
{
        struct nfs4_session *session;
        struct nfs4_slot_table *tbl;
        struct nfs4_slot *slot = res->sr_slot;
        bool send_new_highest_used_slotid = false;

        tbl = slot->table;
        session = tbl->session;

        spin_lock(&tbl->slot_tbl_lock);
        /* Be nice to the server: try to ensure that the last transmitted
         * value for highest_user_slotid <= target_highest_slotid
         */
        if (tbl->highest_used_slotid > tbl->target_highest_slotid)
                send_new_highest_used_slotid = true;

        if (nfs41_wake_and_assign_slot(tbl, slot)) {
                send_new_highest_used_slotid = false;
                goto out_unlock;
        }
        nfs4_free_slot(tbl, slot);

        if (tbl->highest_used_slotid != NFS4_NO_SLOT)
                send_new_highest_used_slotid = false;
out_unlock:
        spin_unlock(&tbl->slot_tbl_lock);
        res->sr_slot = NULL;
        if (send_new_highest_used_slotid)
                nfs41_server_notify_highest_slotid_update(session->clp);
}

int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res)
{
        struct nfs4_session *session;
        struct nfs4_slot *slot = res->sr_slot;
        struct nfs_client *clp;
        bool interrupted = false;
        int ret = 1;

        if (slot == NULL)
                goto out_noaction;
        /* don't increment the sequence number if the task wasn't sent */
        if (!RPC_WAS_SENT(task))
                goto out;

        session = slot->table->session;

        if (slot->interrupted) {
                slot->interrupted = 0;
                interrupted = true;
        }

        trace_nfs4_sequence_done(session, res);
        /* Check the SEQUENCE operation status */
        switch (res->sr_status) {
        case 0:
                /* Update the slot's sequence and clientid lease timer */
                ++slot->seq_nr;
                clp = session->clp;
                do_renew_lease(clp, res->sr_timestamp);
                /* Check sequence flags */
                if (res->sr_status_flags != 0)
                        nfs4_schedule_lease_recovery(clp);
                nfs41_update_target_slotid(slot->table, slot, res);
                break;
        case 1:
                /*
                 * sr_status remains 1 if an RPC level error occurred.
                 * The server may or may not have processed the sequence
                 * operation..
                 * Mark the slot as having hosted an interrupted RPC call.
                 */
                slot->interrupted = 1;
                goto out;
        case -NFS4ERR_DELAY:
                /* The server detected a resend of the RPC call and
                 * returned NFS4ERR_DELAY as per Section 2.10.6.2
                 * of RFC5661.
                 */
                dprintk("%s: slot=%u seq=%u: Operation in progress\n",
                        __func__,
                        slot->slot_nr,
                        slot->seq_nr);
                goto out_retry;
        case -NFS4ERR_BADSLOT:
                /*
                 * The slot id we used was probably retired. Try again
                 * using a different slot id.
                 */
                goto retry_nowait;
        case -NFS4ERR_SEQ_MISORDERED:
                /*
                 * Was the last operation on this sequence interrupted?
                 * If so, retry after bumping the sequence number.
                 */
                if (interrupted) {
                        ++slot->seq_nr;
                        goto retry_nowait;
                }
                /*
                 * Could this slot have been previously retired?
                 * If so, then the server may be expecting seq_nr = 1!
                 */
                if (slot->seq_nr != 1) {
                        slot->seq_nr = 1;
                        goto retry_nowait;
                }
                break;
        case -NFS4ERR_SEQ_FALSE_RETRY:
                ++slot->seq_nr;
                goto retry_nowait;
        default:
                /* Just update the slot sequence no. */
                ++slot->seq_nr;
        }
out:
        /* The session may be reset by one of the error handlers. */
        dprintk("%s: Error %d free the slot \n", __func__, res->sr_status);
        nfs41_sequence_free_slot(res);
out_noaction:
        return ret;
retry_nowait:
        if (rpc_restart_call_prepare(task)) {
                task->tk_status = 0;
                ret = 0;
        }
        goto out;
out_retry:
        if (!rpc_restart_call(task))
                goto out;
        rpc_delay(task, NFS4_POLL_RETRY_MAX);
        return 0;
}
EXPORT_SYMBOL_GPL(nfs41_sequence_done);

static int nfs4_sequence_done(struct rpc_task *task,
                               struct nfs4_sequence_res *res)
{
        if (res->sr_slot == NULL)
                return 1;
        if (!res->sr_slot->table->session)
                return nfs40_sequence_done(task, res);
        return nfs41_sequence_done(task, res);
}

int nfs41_setup_sequence(struct nfs4_session *session,
                                struct nfs4_sequence_args *args,
                                struct nfs4_sequence_res *res,
                                struct rpc_task *task)
{
        struct nfs4_slot *slot;
        struct nfs4_slot_table *tbl;

        dprintk("--> %s\n", __func__);
        /* slot already allocated? */
        if (res->sr_slot != NULL)
                goto out_success;

        tbl = &session->fc_slot_table;

        task->tk_timeout = 0;

        spin_lock(&tbl->slot_tbl_lock);
        if (test_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state) &&
            !args->sa_privileged) {
                /* The state manager will wait until the slot table is empty */
                dprintk("%s session is draining\n", __func__);
                goto out_sleep;
        }

        slot = nfs4_alloc_slot(tbl);
        if (IS_ERR(slot)) {
                /* If out of memory, try again in 1/4 second */
                if (slot == ERR_PTR(-ENOMEM))
                        task->tk_timeout = HZ >> 2;
                dprintk("<-- %s: no free slots\n", __func__);
                goto out_sleep;
        }
        spin_unlock(&tbl->slot_tbl_lock);

        args->sa_slot = slot;

        dprintk("<-- %s slotid=%u seqid=%u\n", __func__,
                        slot->slot_nr, slot->seq_nr);

        res->sr_slot = slot;
        res->sr_timestamp = jiffies;
        res->sr_status_flags = 0;
        /*
         * sr_status is only set in decode_sequence, and so will remain
         * set to 1 if an rpc level failure occurs.
         */
        res->sr_status = 1;
        trace_nfs4_setup_sequence(session, args);
out_success:
        rpc_call_start(task);
        return 0;
out_sleep:
        /* Privileged tasks are queued with top priority */
        if (args->sa_privileged)
                rpc_sleep_on_priority(&tbl->slot_tbl_waitq, task,
                                NULL, RPC_PRIORITY_PRIVILEGED);
        else
                rpc_sleep_on(&tbl->slot_tbl_waitq, task, NULL);
        spin_unlock(&tbl->slot_tbl_lock);
        return -EAGAIN;
}
EXPORT_SYMBOL_GPL(nfs41_setup_sequence);

static int nfs4_setup_sequence(const struct nfs_server *server,
                               struct nfs4_sequence_args *args,
                               struct nfs4_sequence_res *res,
                               struct rpc_task *task)
{
        struct nfs4_session *session = nfs4_get_session(server);
        int ret = 0;

        if (!session)
                return nfs40_setup_sequence(server, args, res, task);

        dprintk("--> %s clp %p session %p sr_slot %u\n",
                __func__, session->clp, session, res->sr_slot ?
                        res->sr_slot->slot_nr : NFS4_NO_SLOT);

        ret = nfs41_setup_sequence(session, args, res, task);

        dprintk("<-- %s status=%d\n", __func__, ret);
        return ret;
}

static void nfs41_call_sync_prepare(struct rpc_task *task, void *calldata)
{
        struct nfs4_call_sync_data *data = calldata;
        struct nfs4_session *session = nfs4_get_session(data->seq_server);

        dprintk("--> %s data->seq_server %p\n", __func__, data->seq_server);

        nfs41_setup_sequence(session, data->seq_args, data->seq_res, task);
}

static void nfs41_call_sync_done(struct rpc_task *task, void *calldata)
{
        struct nfs4_call_sync_data *data = calldata;

        nfs41_sequence_done(task, data->seq_res);
}

static const struct rpc_call_ops nfs41_call_sync_ops = {
        .rpc_call_prepare = nfs41_call_sync_prepare,
        .rpc_call_done = nfs41_call_sync_done,
};

#else   /* !CONFIG_NFS_V4_1 */

static int nfs4_setup_sequence(const struct nfs_server *server,
                               struct nfs4_sequence_args *args,
                               struct nfs4_sequence_res *res,
                               struct rpc_task *task)
{
        return nfs40_setup_sequence(server, args, res, task);
}

static int nfs4_sequence_done(struct rpc_task *task,
                               struct nfs4_sequence_res *res)
{
        return nfs40_sequence_done(task, res);
}

#endif  /* !CONFIG_NFS_V4_1 */

static void nfs40_call_sync_prepare(struct rpc_task *task, void *calldata)
{
        struct nfs4_call_sync_data *data = calldata;
        nfs4_setup_sequence(data->seq_server,
                                data->seq_args, data->seq_res, task);
}

static void nfs40_call_sync_done(struct rpc_task *task, void *calldata)
{
        struct nfs4_call_sync_data *data = calldata;
        nfs4_sequence_done(task, data->seq_res);
}

static const struct rpc_call_ops nfs40_call_sync_ops = {
        .rpc_call_prepare = nfs40_call_sync_prepare,
        .rpc_call_done = nfs40_call_sync_done,
};

static int nfs4_call_sync_sequence(struct rpc_clnt *clnt,
                                   struct nfs_server *server,
                                   struct rpc_message *msg,
                                   struct nfs4_sequence_args *args,
                                   struct nfs4_sequence_res *res)
{
        int ret;
        struct rpc_task *task;
        struct nfs_client *clp = server->nfs_client;
        struct nfs4_call_sync_data data = {
                .seq_server = server,
                .seq_args = args,
                .seq_res = res,
        };
        struct rpc_task_setup task_setup = {
                .rpc_client = clnt,
                .rpc_message = msg,
                .callback_ops = clp->cl_mvops->call_sync_ops,
                .callback_data = &data
        };

        task = rpc_run_task(&task_setup);
        if (IS_ERR(task))
                ret = PTR_ERR(task);
        else {
                ret = task->tk_status;
                rpc_put_task(task);
        }
        return ret;
}

int nfs4_call_sync(struct rpc_clnt *clnt,
                   struct nfs_server *server,
                   struct rpc_message *msg,
                   struct nfs4_sequence_args *args,
                   struct nfs4_sequence_res *res,
                   int cache_reply)
{
        nfs4_init_sequence(args, res, cache_reply);
        return nfs4_call_sync_sequence(clnt, server, msg, args, res);
}

static void update_changeattr(struct inode *dir, struct nfs4_change_info *cinfo)
{
        struct nfs_inode *nfsi = NFS_I(dir);

        spin_lock(&dir->i_lock);
        nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA;
        if (!cinfo->atomic || cinfo->before != dir->i_version)
                nfs_force_lookup_revalidate(dir);
        dir->i_version = cinfo->after;
        nfs_fscache_invalidate(dir);
        spin_unlock(&dir->i_lock);
}

struct nfs4_opendata {
        struct kref kref;
        struct nfs_openargs o_arg;
        struct nfs_openres o_res;
        struct nfs_open_confirmargs c_arg;
        struct nfs_open_confirmres c_res;
        struct nfs4_string owner_name;
        struct nfs4_string group_name;
        struct nfs_fattr f_attr;
        struct nfs4_label *f_label;
        struct dentry *dir;
        struct dentry *dentry;
        struct nfs4_state_owner *owner;
        struct nfs4_state *state;
        struct iattr attrs;
        unsigned long timestamp;
        unsigned int rpc_done : 1;
        unsigned int file_created : 1;
        unsigned int is_recover : 1;
        int rpc_status;
        int cancelled;
};

static bool nfs4_clear_cap_atomic_open_v1(struct nfs_server *server,
                int err, struct nfs4_exception *exception)
{
        if (err != -EINVAL)
                return false;
        if (!(server->caps & NFS_CAP_ATOMIC_OPEN_V1))
                return false;
        server->caps &= ~NFS_CAP_ATOMIC_OPEN_V1;
        exception->retry = 1;
        return true;
}

static enum open_claim_type4
nfs4_map_atomic_open_claim(struct nfs_server *server,
                enum open_claim_type4 claim)
{
        if (server->caps & NFS_CAP_ATOMIC_OPEN_V1)
                return claim;
        switch (claim) {
        default:
                return claim;
        case NFS4_OPEN_CLAIM_FH:
                return NFS4_OPEN_CLAIM_NULL;
        case NFS4_OPEN_CLAIM_DELEG_CUR_FH:
                return NFS4_OPEN_CLAIM_DELEGATE_CUR;
        case NFS4_OPEN_CLAIM_DELEG_PREV_FH:
                return NFS4_OPEN_CLAIM_DELEGATE_PREV;
        }
}

static void nfs4_init_opendata_res(struct nfs4_opendata *p)
{
        p->o_res.f_attr = &p->f_attr;
        p->o_res.f_label = p->f_label;
        p->o_res.seqid = p->o_arg.seqid;
        p->c_res.seqid = p->c_arg.seqid;
        p->o_res.server = p->o_arg.server;
        p->o_res.access_request = p->o_arg.access;
        nfs_fattr_init(&p->f_attr);
        nfs_fattr_init_names(&p->f_attr, &p->owner_name, &p->group_name);
}

static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry,
                struct nfs4_state_owner *sp, fmode_t fmode, int flags,
                const struct iattr *attrs,
                struct nfs4_label *label,
                enum open_claim_type4 claim,
                gfp_t gfp_mask)
{
        struct dentry *parent = dget_parent(dentry);
        struct inode *dir = parent->d_inode;
        struct nfs_server *server = NFS_SERVER(dir);
        struct nfs4_opendata *p;

        p = kzalloc(sizeof(*p), gfp_mask);
        if (p == NULL)
                goto err;

        p->f_label = nfs4_label_alloc(server, gfp_mask);
        if (IS_ERR(p->f_label))
                goto err_free_p;

        p->o_arg.seqid = nfs_alloc_seqid(&sp->so_seqid, gfp_mask);
        if (p->o_arg.seqid == NULL)
                goto err_free_label;
        nfs_sb_active(dentry->d_sb);
        p->dentry = dget(dentry);
        p->dir = parent;
        p->owner = sp;
        atomic_inc(&sp->so_count);
        p->o_arg.open_flags = flags;
        p->o_arg.fmode = fmode & (FMODE_READ|FMODE_WRITE);
        /* don't put an ACCESS op in OPEN compound if O_EXCL, because ACCESS

         * will return permission denied for all bits until close */
        if (!(flags & O_EXCL)) {
                /* ask server to check for all possible rights as results
                 * are cached */
                p->o_arg.access = NFS4_ACCESS_READ | NFS4_ACCESS_MODIFY |
                                  NFS4_ACCESS_EXTEND | NFS4_ACCESS_EXECUTE;
        }
        p->o_arg.clientid = server->nfs_client->cl_clientid;
        p->o_arg.id.create_time = ktime_to_ns(sp->so_seqid.create_time);
        p->o_arg.id.uniquifier = sp->so_seqid.owner_id;
        p->o_arg.name = &dentry->d_name;
        p->o_arg.server = server;
        p->o_arg.bitmask = nfs4_bitmask(server, label);
        p->o_arg.open_bitmap = &nfs4_fattr_bitmap[0];
        p->o_arg.label = label;
        p->o_arg.claim = nfs4_map_atomic_open_claim(server, claim);
        switch (p->o_arg.claim) {
        case NFS4_OPEN_CLAIM_NULL:
        case NFS4_OPEN_CLAIM_DELEGATE_CUR:
        case NFS4_OPEN_CLAIM_DELEGATE_PREV:
                p->o_arg.fh = NFS_FH(dir);
                break;
        case NFS4_OPEN_CLAIM_PREVIOUS:
        case NFS4_OPEN_CLAIM_FH:
        case NFS4_OPEN_CLAIM_DELEG_CUR_FH:
        case NFS4_OPEN_CLAIM_DELEG_PREV_FH:
                p->o_arg.fh = NFS_FH(dentry->d_inode);
        }
        if (attrs != NULL && attrs->ia_valid != 0) {
                __u32 verf[2];

                p->o_arg.u.attrs = &p->attrs;
                memcpy(&p->attrs, attrs, sizeof(p->attrs));

                verf[0] = jiffies;
                verf[1] = current->pid;
                memcpy(p->o_arg.u.verifier.data, verf,
                                sizeof(p->o_arg.u.verifier.data));
        }
        p->c_arg.fh = &p->o_res.fh;
        p->c_arg.stateid = &p->o_res.stateid;
        p->c_arg.seqid = p->o_arg.seqid;
        nfs4_init_opendata_res(p);
        kref_init(&p->kref);
        return p;

err_free_label:
        nfs4_label_free(p->f_label);
err_free_p:
        kfree(p);
err:
        dput(parent);
        return NULL;
}

static void nfs4_opendata_free(struct kref *kref)
{
        struct nfs4_opendata *p = container_of(kref,
                        struct nfs4_opendata, kref);
        struct super_block *sb = p->dentry->d_sb;

        nfs_free_seqid(p->o_arg.seqid);
        if (p->state != NULL)
                nfs4_put_open_state(p->state);
        nfs4_put_state_owner(p->owner);

        nfs4_label_free(p->f_label);

        dput(p->dir);
        dput(p->dentry);
        nfs_sb_deactive(sb);
        nfs_fattr_free_names(&p->f_attr);
        kfree(p->f_attr.mdsthreshold);
        kfree(p);
}

static void nfs4_opendata_put(struct nfs4_opendata *p)
{
        if (p != NULL)
                kref_put(&p->kref, nfs4_opendata_free);
}

static int nfs4_wait_for_completion_rpc_task(struct rpc_task *task)
{
        int ret;

        ret = rpc_wait_for_completion_task(task);
        return ret;
}

static int can_open_cached(struct nfs4_state *state, fmode_t mode, int open_mode)
{
        int ret = 0;

        if (open_mode & (O_EXCL|O_TRUNC))
                goto out;
        switch (mode & (FMODE_READ|FMODE_WRITE)) {
                case FMODE_READ:
                        ret |= test_bit(NFS_O_RDONLY_STATE, &state->flags) != 0
                                && state->n_rdonly != 0;
                        break;
                case FMODE_WRITE:
                        ret |= test_bit(NFS_O_WRONLY_STATE, &state->flags) != 0
                                && state->n_wronly != 0;
                        break;
                case FMODE_READ|FMODE_WRITE:
                        ret |= test_bit(NFS_O_RDWR_STATE, &state->flags) != 0
                                && state->n_rdwr != 0;
        }
out:
        return ret;
}

static int can_open_delegated(struct nfs_delegation *delegation, fmode_t fmode)
{
        if (delegation == NULL)
                return 0;
        if ((delegation->type & fmode) != fmode)
                return 0;
        if (test_bit(NFS_DELEGATION_RETURNING, &delegation->flags))
                return 0;
        nfs_mark_delegation_referenced(delegation);
        return 1;
}

static void update_open_stateflags(struct nfs4_state *state, fmode_t fmode)
{
        switch (fmode) {
                case FMODE_WRITE:
                        state->n_wronly++;
                        break;
                case FMODE_READ:
                        state->n_rdonly++;
                        break;
                case FMODE_READ|FMODE_WRITE:
                        state->n_rdwr++;
        }
        nfs4_state_set_mode_locked(state, state->state | fmode);
}

static void nfs_test_and_clear_all_open_stateid(struct nfs4_state *state)
{
        struct nfs_client *clp = state->owner->so_server->nfs_client;
        bool need_recover = false;

        if (test_and_clear_bit(NFS_O_RDONLY_STATE, &state->flags) && state->n_rdonly)
                need_recover = true;
        if (test_and_clear_bit(NFS_O_WRONLY_STATE, &state->flags) && state->n_wronly)
                need_recover = true;
        if (test_and_clear_bit(NFS_O_RDWR_STATE, &state->flags) && state->n_rdwr)
                need_recover = true;
        if (need_recover)
                nfs4_state_mark_reclaim_nograce(clp, state);
}

static bool nfs_need_update_open_stateid(struct nfs4_state *state,
                nfs4_stateid *stateid)
{
        if (test_and_set_bit(NFS_OPEN_STATE, &state->flags) == 0)
                return true;
        if (!nfs4_stateid_match_other(stateid, &state->open_stateid)) {
                nfs_test_and_clear_all_open_stateid(state);
                return true;
        }
        if (nfs4_stateid_is_newer(stateid, &state->open_stateid))
                return true;
        return false;
}

static void nfs_clear_open_stateid_locked(struct nfs4_state *state,
                nfs4_stateid *stateid, fmode_t fmode)
{
        clear_bit(NFS_O_RDWR_STATE, &state->flags);
        switch (fmode & (FMODE_READ|FMODE_WRITE)) {
        case FMODE_WRITE:
                clear_bit(NFS_O_RDONLY_STATE, &state->flags);
                break;
        case FMODE_READ:
                clear_bit(NFS_O_WRONLY_STATE, &state->flags);
                break;
        case 0:
                clear_bit(NFS_O_RDONLY_STATE, &state->flags);
                clear_bit(NFS_O_WRONLY_STATE, &state->flags);
                clear_bit(NFS_OPEN_STATE, &state->flags);
        }
        if (stateid == NULL)
                return;
        if (!nfs_need_update_open_stateid(state, stateid))
                return;
        if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0)
                nfs4_stateid_copy(&state->stateid, stateid);
        nfs4_stateid_copy(&state->open_stateid, stateid);
}

static void nfs_clear_open_stateid(struct nfs4_state *state, nfs4_stateid *stateid, fmode_t fmode)
{
        write_seqlock(&state->seqlock);
        nfs_clear_open_stateid_locked(state, stateid, fmode);
        write_sequnlock(&state->seqlock);
        if (test_bit(NFS_STATE_RECLAIM_NOGRACE, &state->flags))
                nfs4_schedule_state_manager(state->owner->so_server->nfs_client);
}

static void nfs_set_open_stateid_locked(struct nfs4_state *state, nfs4_stateid *stateid, fmode_t fmode)
{
        switch (fmode) {
                case FMODE_READ:
                        set_bit(NFS_O_RDONLY_STATE, &state->flags);
                        break;
                case FMODE_WRITE:
                        set_bit(NFS_O_WRONLY_STATE, &state->flags);
                        break;
                case FMODE_READ|FMODE_WRITE:
                        set_bit(NFS_O_RDWR_STATE, &state->flags);
        }
        if (!nfs_need_update_open_stateid(state, stateid))
                return;
        if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0)
                nfs4_stateid_copy(&state->stateid, stateid);
        nfs4_stateid_copy(&state->open_stateid, stateid);
}

static void __update_open_stateid(struct nfs4_state *state, nfs4_stateid *open_stateid, const nfs4_stateid *deleg_stateid, fmode_t fmode)
{
        /*
         * Protect the call to nfs4_state_set_mode_locked and
         * serialise the stateid update
         */
        write_seqlock(&state->seqlock);
        if (deleg_stateid != NULL) {
                nfs4_stateid_copy(&state->stateid, deleg_stateid);
                set_bit(NFS_DELEGATED_STATE, &state->flags);
        }
        if (open_stateid != NULL)
                nfs_set_open_stateid_locked(state, open_stateid, fmode);
        write_sequnlock(&state->seqlock);
        spin_lock(&state->owner->so_lock);
        update_open_stateflags(state, fmode);
        spin_unlock(&state->owner->so_lock);
}

static int update_open_stateid(struct nfs4_state *state, nfs4_stateid *open_stateid, nfs4_stateid *delegation, fmode_t fmode)
{
        struct nfs_inode *nfsi = NFS_I(state->inode);
        struct nfs_delegation *deleg_cur;
        int ret = 0;

        fmode &= (FMODE_READ|FMODE_WRITE);

        rcu_read_lock();
        deleg_cur = rcu_dereference(nfsi->delegation);
        if (deleg_cur == NULL)
                goto no_delegation;

        spin_lock(&deleg_cur->lock);
        if (rcu_dereference(nfsi->delegation) != deleg_cur ||
           test_bit(NFS_DELEGATION_RETURNING, &deleg_cur->flags) ||
            (deleg_cur->type & fmode) != fmode)
                goto no_delegation_unlock;

        if (delegation == NULL)
                delegation = &deleg_cur->stateid;
        else if (!nfs4_stateid_match(&deleg_cur->stateid, delegation))
                goto no_delegation_unlock;

        nfs_mark_delegation_referenced(deleg_cur);
        __update_open_stateid(state, open_stateid, &deleg_cur->stateid, fmode);
        ret = 1;
no_delegation_unlock:
        spin_unlock(&deleg_cur->lock);
no_delegation:
        rcu_read_unlock();

        if (!ret && open_stateid != NULL) {
                __update_open_stateid(state, open_stateid, NULL, fmode);
                ret = 1;
        }
        if (test_bit(NFS_STATE_RECLAIM_NOGRACE, &state->flags))
                nfs4_schedule_state_manager(state->owner->so_server->nfs_client);

        return ret;
}


static void nfs4_return_incompatible_delegation(struct inode *inode, fmode_t fmode)
{
        struct nfs_delegation *delegation;

        rcu_read_lock();
        delegation = rcu_dereference(NFS_I(inode)->delegation);
        if (delegation == NULL || (delegation->type & fmode) == fmode) {
                rcu_read_unlock();
                return;
        }
        rcu_read_unlock();
        nfs4_inode_return_delegation(inode);
}

static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata)
{
        struct nfs4_state *state = opendata->state;
        struct nfs_inode *nfsi = NFS_I(state->inode);
        struct nfs_delegation *delegation;
        int open_mode = opendata->o_arg.open_flags;
        fmode_t fmode = opendata->o_arg.fmode;
        nfs4_stateid stateid;
        int ret = -EAGAIN;

        for (;;) {
                spin_lock(&state->owner->so_lock);
                if (can_open_cached(state, fmode, open_mode)) {
                        update_open_stateflags(state, fmode);
                        spin_unlock(&state->owner->so_lock);
                        goto out_return_state;
                }
                spin_unlock(&state->owner->so_lock);
                rcu_read_lock();
                delegation = rcu_dereference(nfsi->delegation);
                if (!can_open_delegated(delegation, fmode)) {
                        rcu_read_unlock();
                        break;
                }
                /* Save the delegation */
                nfs4_stateid_copy(&stateid, &delegation->stateid);
                rcu_read_unlock();
                nfs_release_seqid(opendata->o_arg.seqid);
                if (!opendata->is_recover) {
                        ret = nfs_may_open(state->inode, state->owner->so_cred, open_mode);
                        if (ret != 0)
                                goto out;
                }
                ret = -EAGAIN;

                /* Try to update the stateid using the delegation */
                if (update_open_stateid(state, NULL, &stateid, fmode))
                        goto out_return_state;
        }
out:
        return ERR_PTR(ret);
out_return_state:
        atomic_inc(&state->count);
        return state;
}

static void
nfs4_opendata_check_deleg(struct nfs4_opendata *data, struct nfs4_state *state)
{
        struct nfs_client *clp = NFS_SERVER(state->inode)->nfs_client;
        struct nfs_delegation *delegation;
        int delegation_flags = 0;

        rcu_read_lock();
        delegation = rcu_dereference(NFS_I(state->inode)->delegation);
        if (delegation)
                delegation_flags = delegation->flags;
        rcu_read_unlock();
        if (data->o_arg.claim == NFS4_OPEN_CLAIM_DELEGATE_CUR) {
                pr_err_ratelimited("NFS: Broken NFSv4 server %s is "
                                   "returning a delegation for "
                                   "OPEN(CLAIM_DELEGATE_CUR)\n",
                                   clp->cl_hostname);
        } else if ((delegation_flags & 1UL<<NFS_DELEGATION_NEED_RECLAIM) == 0)
                nfs_inode_set_delegation(state->inode,
                                         data->owner->so_cred,
                                         &data->o_res);
        else
                nfs_inode_reclaim_delegation(state->inode,
                                             data->owner->so_cred,
                                             &data->o_res);
}

/*
 * Check the inode attributes against the CLAIM_PREVIOUS returned attributes
 * and update the nfs4_state.
 */
static struct nfs4_state *
_nfs4_opendata_reclaim_to_nfs4_state(struct nfs4_opendata *data)
{
        struct inode *inode = data->state->inode;
        struct nfs4_state *state = data->state;
        int ret;

        if (!data->rpc_done) {
                if (data->rpc_status) {
                        ret = data->rpc_status;
                        goto err;
                }
                /* cached opens have already been processed */
                goto update;
        }

        ret = nfs_refresh_inode(inode, &data->f_attr);
        if (ret)
                goto err;

        if (data->o_res.delegation_type != 0)
                nfs4_opendata_check_deleg(data, state);
update:
        update_open_stateid(state, &data->o_res.stateid, NULL,
                            data->o_arg.fmode);
        atomic_inc(&state->count);

        return state;
err:
        return ERR_PTR(ret);

}

static struct nfs4_state *
_nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data)
{
        struct inode *inode;
        struct nfs4_state *state = NULL;
        int ret;

        if (!data->rpc_done) {
                state = nfs4_try_open_cached(data);
                goto out;
        }

        ret = -EAGAIN;
        if (!(data->f_attr.valid & NFS_ATTR_FATTR))
                goto err;
        inode = nfs_fhget(data->dir->d_sb, &data->o_res.fh, &data->f_attr, data->f_label);
        ret = PTR_ERR(inode);
        if (IS_ERR(inode))
                goto err;
        ret = -ENOMEM;
        state = nfs4_get_open_state(inode, data->owner);
        if (state == NULL)
                goto err_put_inode;
        if (data->o_res.delegation_type != 0)
                nfs4_opendata_check_deleg(data, state);
        update_open_stateid(state, &data->o_res.stateid, NULL,
                        data->o_arg.fmode);
        iput(inode);
out:
        nfs_release_seqid(data->o_arg.seqid);
        return state;
err_put_inode:
        iput(inode);
err:
        return ERR_PTR(ret);
}

static struct nfs4_state *
nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data)
{
        if (data->o_arg.claim == NFS4_OPEN_CLAIM_PREVIOUS)
                return _nfs4_opendata_reclaim_to_nfs4_state(data);
        return _nfs4_opendata_to_nfs4_state(data);
}

static struct nfs_open_context *nfs4_state_find_open_context(struct nfs4_state *state)
{
        struct nfs_inode *nfsi = NFS_I(state->inode);
        struct nfs_open_context *ctx;

        spin_lock(&state->inode->i_lock);
        list_for_each_entry(ctx, &nfsi->open_files, list) {
                if (ctx->state != state)
                        continue;
                get_nfs_open_context(ctx);
                spin_unlock(&state->inode->i_lock);
                return ctx;
        }
        spin_unlock(&state->inode->i_lock);
        return ERR_PTR(-ENOENT);
}

static struct nfs4_opendata *nfs4_open_recoverdata_alloc(struct nfs_open_context *ctx,
                struct nfs4_state *state, enum open_claim_type4 claim)
{
        struct nfs4_opendata *opendata;

        opendata = nfs4_opendata_alloc(ctx->dentry, state->owner, 0, 0,
                        NULL, NULL, claim, GFP_NOFS);
        if (opendata == NULL)
                return ERR_PTR(-ENOMEM);
        opendata->state = state;
        atomic_inc(&state->count);
        return opendata;
}

static int nfs4_open_recover_helper(struct nfs4_opendata *opendata, fmode_t fmode, struct nfs4_state **res)
{
        struct nfs4_state *newstate;
        int ret;

        opendata->o_arg.open_flags = 0;
        opendata->o_arg.fmode = fmode;
        memset(&opendata->o_res, 0, sizeof(opendata->o_res));
        memset(&opendata->c_res, 0, sizeof(opendata->c_res));
        nfs4_init_opendata_res(opendata);
        ret = _nfs4_recover_proc_open(opendata);
        if (ret != 0)
                return ret; 
        newstate = nfs4_opendata_to_nfs4_state(opendata);
        if (IS_ERR(newstate))
                return PTR_ERR(newstate);
        nfs4_close_state(newstate, fmode);
        *res = newstate;
        return 0;
}

static int nfs4_open_recover(struct nfs4_opendata *opendata, struct nfs4_state *state)
{
        struct nfs4_state *newstate;
        int ret;

        /* Don't trigger recovery in nfs_test_and_clear_all_open_stateid */
        clear_bit(NFS_O_RDWR_STATE, &state->flags);
        clear_bit(NFS_O_WRONLY_STATE, &state->flags);
        clear_bit(NFS_O_RDONLY_STATE, &state->flags);
        /* memory barrier prior to reading state->n_* */
        clear_bit(NFS_DELEGATED_STATE, &state->flags);
        clear_bit(NFS_OPEN_STATE, &state->flags);
        smp_rmb();
        if (state->n_rdwr != 0) {
                ret = nfs4_open_recover_helper(opendata, FMODE_READ|FMODE_WRITE, &newstate);
                if (ret != 0)
                        return ret;
                if (newstate != state)
                        return -ESTALE;
        }
        if (state->n_wronly != 0) {
                ret = nfs4_open_recover_helper(opendata, FMODE_WRITE, &newstate);
                if (ret != 0)
                        return ret;
                if (newstate != state)
                        return -ESTALE;
        }
        if (state->n_rdonly != 0) {
                ret = nfs4_open_recover_helper(opendata, FMODE_READ, &newstate);
                if (ret != 0)
                        return ret;
                if (newstate != state)
                        return -ESTALE;
        }
        /*
         * We may have performed cached opens for all three recoveries.
         * Check if we need to update the current stateid.
         */
        if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0 &&
            !nfs4_stateid_match(&state->stateid, &state->open_stateid)) {
                write_seqlock(&state->seqlock);
                if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0)
                        nfs4_stateid_copy(&state->stateid, &state->open_stateid);
                write_sequnlock(&state->seqlock);
        }
        return 0;
}

/*
 * OPEN_RECLAIM:
 *      reclaim state on the server after a reboot.
 */
static int _nfs4_do_open_reclaim(struct nfs_open_context *ctx, struct nfs4_state *state)
{
        struct nfs_delegation *delegation;
        struct nfs4_opendata *opendata;
        fmode_t delegation_type = 0;
        int status;

        opendata = nfs4_open_recoverdata_alloc(ctx, state,
                        NFS4_OPEN_CLAIM_PREVIOUS);
        if (IS_ERR(opendata))
                return PTR_ERR(opendata);
        rcu_read_lock();
        delegation = rcu_dereference(NFS_I(state->inode)->delegation);
        if (delegation != NULL && test_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags) != 0)
                delegation_type = delegation->type;
        rcu_read_unlock();
        opendata->o_arg.u.delegation_type = delegation_type;
        status = nfs4_open_recover(opendata, state);
        nfs4_opendata_put(opendata);
        return status;
}

static int nfs4_do_open_reclaim(struct nfs_open_context *ctx, struct nfs4_state *state)
{
        struct nfs_server *server = NFS_SERVER(state->inode);
        struct nfs4_exception exception = { };
        int err;
        do {
                err = _nfs4_do_open_reclaim(ctx, state);
                trace_nfs4_open_reclaim(ctx, 0, err);
                if (nfs4_clear_cap_atomic_open_v1(server, err, &exception))
                        continue;
                if (err != -NFS4ERR_DELAY)
                        break;
                nfs4_handle_exception(server, err, &exception);
        } while (exception.retry);
        return err;
}

static int nfs4_open_reclaim(struct nfs4_state_owner *sp, struct nfs4_state *state)
{
        struct nfs_open_context *ctx;
        int ret;

        ctx = nfs4_state_find_open_context(state);
        if (IS_ERR(ctx))
                return -EAGAIN;
        ret = nfs4_do_open_reclaim(ctx, state);
        put_nfs_open_context(ctx);
        return ret;
}

static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct nfs4_state *state, const nfs4_stateid *stateid, int err)
{
        switch (err) {
                default:
                        printk(KERN_ERR "NFS: %s: unhandled error "
                                        "%d.\n", __func__, err);
                case 0:
                case -ENOENT:
                case -ESTALE:
                        break;
                case -NFS4ERR_BADSESSION:
                case -NFS4ERR_BADSLOT:
                case -NFS4ERR_BAD_HIGH_SLOT:
                case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
                case -NFS4ERR_DEADSESSION:
                        set_bit(NFS_DELEGATED_STATE, &state->flags);
                        nfs4_schedule_session_recovery(server->nfs_client->cl_session, err);
                        return -EAGAIN;
                case -NFS4ERR_STALE_CLIENTID:
                case -NFS4ERR_STALE_STATEID:
                        set_bit(NFS_DELEGATED_STATE, &state->flags);
                case -NFS4ERR_EXPIRED:
                        /* Don't recall a delegation if it was lost */
                        nfs4_schedule_lease_recovery(server->nfs_client);
                        return -EAGAIN;
                case -NFS4ERR_MOVED:
                        nfs4_schedule_migration_recovery(server);
                        return -EAGAIN;
                case -NFS4ERR_LEASE_MOVED:
                        nfs4_schedule_lease_moved_recovery(server->nfs_client);
                        return -EAGAIN;
                case -NFS4ERR_DELEG_REVOKED:
                case -NFS4ERR_ADMIN_REVOKED:
                case -NFS4ERR_BAD_STATEID:
                case -NFS4ERR_OPENMODE:
                        nfs_inode_find_state_and_recover(state->inode,
                                        stateid);
                        nfs4_schedule_stateid_recovery(server, state);
                        return -EAGAIN;
                case -NFS4ERR_DELAY:
                case -NFS4ERR_GRACE:
                        set_bit(NFS_DELEGATED_STATE, &state->flags);
                        ssleep(1);
                        return -EAGAIN;
                case -ENOMEM:
                case -NFS4ERR_DENIED:
                        /* kill_proc(fl->fl_pid, SIGLOST, 1); */
                        return 0;
        }
        return err;
}

int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid)
{
        struct nfs_server *server = NFS_SERVER(state->inode);
        struct nfs4_opendata *opendata;
        int err;

        opendata = nfs4_open_recoverdata_alloc(ctx, state,
                        NFS4_OPEN_CLAIM_DELEG_CUR_FH);
        if (IS_ERR(opendata))
                return PTR_ERR(opendata);
        nfs4_stateid_copy(&opendata->o_arg.u.delegation, stateid);
        err = nfs4_open_recover(opendata, state);
        nfs4_opendata_put(opendata);
        return nfs4_handle_delegation_recall_error(server, state, stateid, err);
}

static void nfs4_open_confirm_prepare(struct rpc_task *task, void *calldata)
{
        struct nfs4_opendata *data = calldata;

        nfs40_setup_sequence(data->o_arg.server, &data->c_arg.seq_args,
                                &data->c_res.seq_res, task);
}

static void nfs4_open_confirm_done(struct rpc_task *task, void *calldata)
{
        struct nfs4_opendata *data = calldata;

        nfs40_sequence_done(task, &data->c_res.seq_res);

        data->rpc_status = task->tk_status;
        if (data->rpc_status == 0) {
                nfs4_stateid_copy(&data->o_res.stateid, &data->c_res.stateid);
                nfs_confirm_seqid(&data->owner->so_seqid, 0);
                renew_lease(data->o_res.server, data->timestamp);
                data->rpc_done = 1;
        }
}

static void nfs4_open_confirm_release(void *calldata)
{
        struct nfs4_opendata *data = calldata;
        struct nfs4_state *state = NULL;

        /* If this request hasn't been cancelled, do nothing */
        if (data->cancelled == 0)
                goto out_free;
        /* In case of error, no cleanup! */
        if (!data->rpc_done)
                goto out_free;
        state = nfs4_opendata_to_nfs4_state(data);
        if (!IS_ERR(state))
                nfs4_close_state(state, data->o_arg.fmode);
out_free:
        nfs4_opendata_put(data);
}

static const struct rpc_call_ops nfs4_open_confirm_ops = {
        .rpc_call_prepare = nfs4_open_confirm_prepare,
        .rpc_call_done = nfs4_open_confirm_done,
        .rpc_release = nfs4_open_confirm_release,
};

/*
 * Note: On error, nfs4_proc_open_confirm will free the struct nfs4_opendata
 */
static int _nfs4_proc_open_confirm(struct nfs4_opendata *data)
{
        struct nfs_server *server = NFS_SERVER(data->dir->d_inode);
        struct rpc_task *task;
        struct  rpc_message msg = {
                .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN_CONFIRM],
                .rpc_argp = &data->c_arg,
                .rpc_resp = &data->c_res,
                .rpc_cred = data->owner->so_cred,
        };
        struct rpc_task_setup task_setup_data = {
                .rpc_client = server->client,
                .rpc_message = &msg,
                .callback_ops = &nfs4_open_confirm_ops,
                .callback_data = data,
                .workqueue = nfsiod_workqueue,
                .flags = RPC_TASK_ASYNC,
        };
        int status;

        nfs4_init_sequence(&data->c_arg.seq_args, &data->c_res.seq_res, 1);
        kref_get(&data->kref);
        data->rpc_done = 0;
        data->rpc_status = 0;
        data->timestamp = jiffies;
        task = rpc_run_task(&task_setup_data);
        if (IS_ERR(task))
                return PTR_ERR(task);
        status = nfs4_wait_for_completion_rpc_task(task);
        if (status != 0) {
                data->cancelled = 1;
                smp_wmb();
        } else
                status = data->rpc_status;
        rpc_put_task(task);
        return status;
}

static void nfs4_open_prepare(struct rpc_task *task, void *calldata)
{
        struct nfs4_opendata *data = calldata;
        struct nfs4_state_owner *sp = data->owner;
        struct nfs_client *clp = sp->so_server->nfs_client;

        if (nfs_wait_on_sequence(data->o_arg.seqid, task) != 0)
                goto out_wait;
        /*
         * Check if we still need to send an OPEN call, or if we can use
         * a delegation instead.
         */
        if (data->state != NULL) {
                struct nfs_delegation *delegation;

                if (can_open_cached(data->state, data->o_arg.fmode, data->o_arg.open_flags))
                        goto out_no_action;
                rcu_read_lock();
                delegation = rcu_dereference(NFS_I(data->state->inode)->delegation);
                if (data->o_arg.claim != NFS4_OPEN_CLAIM_DELEGATE_CUR &&
                    data->o_arg.claim != NFS4_OPEN_CLAIM_DELEG_CUR_FH &&
                    can_open_delegated(delegation, data->o_arg.fmode))
                        goto unlock_no_action;
                rcu_read_unlock();
        }
        /* Update client id. */
        data->o_arg.clientid = clp->cl_clientid;
        switch (data->o_arg.claim) {
        case NFS4_OPEN_CLAIM_PREVIOUS:
        case NFS4_OPEN_CLAIM_DELEG_CUR_FH:
        case NFS4_OPEN_CLAIM_DELEG_PREV_FH:
                data->o_arg.open_bitmap = &nfs4_open_noattr_bitmap[0];
        case NFS4_OPEN_CLAIM_FH:
                task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN_NOATTR];
                nfs_copy_fh(&data->o_res.fh, data->o_arg.fh);
        }
        data->timestamp = jiffies;
        if (nfs4_setup_sequence(data->o_arg.server,
                                &data->o_arg.seq_args,
                                &data->o_res.seq_res,
                                task) != 0)
                nfs_release_seqid(data->o_arg.seqid);

        /* Set the create mode (note dependency on the session type) */
        data->o_arg.createmode = NFS4_CREATE_UNCHECKED;
        if (data->o_arg.open_flags & O_EXCL) {
                data->o_arg.createmode = NFS4_CREATE_EXCLUSIVE;
                if (nfs4_has_persistent_session(clp))
                        data->o_arg.createmode = NFS4_CREATE_GUARDED;
                else if (clp->cl_mvops->minor_version > 0)
                        data->o_arg.createmode = NFS4_CREATE_EXCLUSIVE4_1;
        }
        return;
unlock_no_action:
        rcu_read_unlock();
out_no_action:
        task->tk_action = NULL;
out_wait:
        nfs4_sequence_done(task, &data->o_res.seq_res);
}

static void nfs4_open_done(struct rpc_task *task, void *calldata)
{
        struct nfs4_opendata *data = calldata;

        data->rpc_status = task->tk_status;

        if (!nfs4_sequence_done(task, &data->o_res.seq_res))
                return;

        if (task->tk_status == 0) {
                if (data->o_res.f_attr->valid & NFS_ATTR_FATTR_TYPE) {
                        switch (data->o_res.f_attr->mode & S_IFMT) {
                        case S_IFREG:
                                break;
                        case S_IFLNK:
                                data->rpc_status = -ELOOP;
                                break;
                        case S_IFDIR:
                                data->rpc_status = -EISDIR;
                                break;
                        default:
                                data->rpc_status = -ENOTDIR;
                        }
                }
                renew_lease(data->o_res.server, data->timestamp);
                if (!(data->o_res.rflags & NFS4_OPEN_RESULT_CONFIRM))
                        nfs_confirm_seqid(&data->owner->so_seqid, 0);
        }
        data->rpc_done = 1;
}

static void nfs4_open_release(void *calldata)
{
        struct nfs4_opendata *data = calldata;
        struct nfs4_state *state = NULL;

        /* If this request hasn't been cancelled, do nothing */
        if (data->cancelled == 0)
                goto out_free;
        /* In case of error, no cleanup! */
        if (data->rpc_status != 0 || !data->rpc_done)
                goto out_free;
        /* In case we need an open_confirm, no cleanup! */
        if (data->o_res.rflags & NFS4_OPEN_RESULT_CONFIRM)
                goto out_free;
        state = nfs4_opendata_to_nfs4_state(data);
        if (!IS_ERR(state))
                nfs4_close_state(state, data->o_arg.fmode);
out_free:
        nfs4_opendata_put(data);
}

static const struct rpc_call_ops nfs4_open_ops = {
        .rpc_call_prepare = nfs4_open_prepare,
        .rpc_call_done = nfs4_open_done,
        .rpc_release = nfs4_open_release,
};

static int nfs4_run_open_task(struct nfs4_opendata *data, int isrecover)
{
        struct inode *dir = data->dir->d_inode;
        struct nfs_server *server = NFS_SERVER(dir);
        struct nfs_openargs *o_arg = &data->o_arg;
        struct nfs_openres *o_res = &data->o_res;
        struct rpc_task *task;
        struct rpc_message msg = {
                .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN],
                .rpc_argp = o_arg,
                .rpc_resp = o_res,
                .rpc_cred = data->owner->so_cred,
        };
        struct rpc_task_setup task_setup_data = {
                .rpc_client = server->client,
                .rpc_message = &msg,
                .callback_ops = &nfs4_open_ops,
                .callback_data = data,
                .workqueue = nfsiod_workqueue,
                .flags = RPC_TASK_ASYNC,
        };
        int status;

        nfs4_init_sequence(&o_arg->seq_args, &o_res->seq_res, 1);
        kref_get(&data->kref);
        data->rpc_done = 0;
        data->rpc_status = 0;
        data->cancelled = 0;
        data->is_recover = 0;
        if (isrecover) {
                nfs4_set_sequence_privileged(&o_arg->seq_args);
                data->is_recover = 1;
        }
        task = rpc_run_task(&task_setup_data);
        if (IS_ERR(task))
                return PTR_ERR(task);
        status = nfs4_wait_for_completion_rpc_task(task);
        if (status != 0) {
                data->cancelled = 1;
                smp_wmb();
        } else
                status = data->rpc_status;
        rpc_put_task(task);

        return status;
}

static int _nfs4_recover_proc_open(struct nfs4_opendata *data)
{
        struct inode *dir = data->dir->d_inode;
        struct nfs_openres *o_res = &data->o_res;
        int status;

        status = nfs4_run_open_task(data, 1);
        if (status != 0 || !data->rpc_done)
                return status;

        nfs_fattr_map_and_free_names(NFS_SERVER(dir), &data->f_attr);

        if (o_res->rflags & NFS4_OPEN_RESULT_CONFIRM) {
                status = _nfs4_proc_open_confirm(data);
                if (status != 0)
                        return status;
        }

        return status;
}

/*
 * Additional permission checks in order to distinguish between an
 * open for read, and an open for execute. This works around the
 * fact that NFSv4 OPEN treats read and execute permissions as being
 * the same.
 * Note that in the non-execute case, we want to turn off permission
 * checking if we just created a new file (POSIX open() semantics).
 */
static int nfs4_opendata_access(struct rpc_cred *cred,
                                struct nfs4_opendata *opendata,
                                struct nfs4_state *state, fmode_t fmode,
                                int openflags)
{
        struct nfs_access_entry cache;
        u32 mask;

        /* access call failed or for some reason the server doesn't
         * support any access modes -- defer access call until later */
        if (opendata->o_res.access_supported == 0)
                return 0;

        mask = 0;
        /*
         * Use openflags to check for exec, because fmode won't
         * always have FMODE_EXEC set when file open for exec.
         */
        if (openflags & __FMODE_EXEC) {
                /* ONLY check for exec rights */
                mask = MAY_EXEC;
        } else if ((fmode & FMODE_READ) && !opendata->file_created)
                mask = MAY_READ;

        cache.cred = cred;
        cache.jiffies = jiffies;
        nfs_access_set_mask(&cache, opendata->o_res.access_result);
        nfs_access_add_cache(state->inode, &cache);

        if ((mask & ~cache.mask & (MAY_READ | MAY_EXEC)) == 0)
                return 0;

        /* even though OPEN succeeded, access is denied. Close the file */
        nfs4_close_state(state, fmode);
        return -EACCES;
}

/*
 * Note: On error, nfs4_proc_open will free the struct nfs4_opendata
 */

static int _nfs4_proc_open(struct nfs4_opendata *data)
{
        struct inode *dir = data->dir->d_inode;
        struct nfs_server *server = NFS_SERVER(dir);
        struct nfs_openargs *o_arg = &data->o_arg;
        struct nfs_openres *o_res = &data->o_res;
        int status;

        status = nfs4_run_open_task(data, 0);
        if (!data->rpc_done)
                return status;
        if (status != 0) {
                if (status == -NFS4ERR_BADNAME &&
                                !(o_arg->open_flags & O_CREAT))
                        return -ENOENT;
                return status;
        }

        nfs_fattr_map_and_free_names(server, &data->f_attr);

        if (o_arg->open_flags & O_CREAT) {
                update_changeattr(dir, &o_res->cinfo);
                if (o_arg->open_flags & O_EXCL)
                        data->file_created = 1;
                else if (o_res->cinfo.before != o_res->cinfo.after)
                        data->file_created = 1;
        }
        if ((o_res->rflags & NFS4_OPEN_RESULT_LOCKTYPE_POSIX) == 0)
                server->caps &= ~NFS_CAP_POSIX_LOCK;
        if(o_res->rflags & NFS4_OPEN_RESULT_CONFIRM) {
                status = _nfs4_proc_open_confirm(data);
                if (status != 0)
                        return status;
        }
        if (!(o_res->f_attr->valid & NFS_ATTR_FATTR))
                nfs4_proc_getattr(server, &o_res->fh, o_res->f_attr, o_res->f_label);
        return 0;
}

static int nfs4_recover_expired_lease(struct nfs_server *server)
{
        return nfs4_client_recover_expired_lease(server->nfs_client);
}

/*
 * OPEN_EXPIRED:
 *      reclaim state on the server after a network partition.
 *      Assumes caller holds the appropriate lock
 */
static int _nfs4_open_expired(struct nfs_open_context *ctx, struct nfs4_state *state)
{
        struct nfs4_opendata *opendata;
        int ret;

        opendata = nfs4_open_recoverdata_alloc(ctx, state,
                        NFS4_OPEN_CLAIM_FH);
        if (IS_ERR(opendata))
                return PTR_ERR(opendata);
        ret = nfs4_open_recover(opendata, state);
        if (ret == -ESTALE)
                d_drop(ctx->dentry);
        nfs4_opendata_put(opendata);
        return ret;
}

static int nfs4_do_open_expired(struct nfs_open_context *ctx, struct nfs4_state *state)
{
        struct nfs_server *server = NFS_SERVER(state->inode);
        struct nfs4_exception exception = { };
        int err;

        do {
                err = _nfs4_open_expired(ctx, state);
                trace_nfs4_open_expired(ctx, 0, err);
                if (nfs4_clear_cap_atomic_open_v1(server, err, &exception))
                        continue;
                switch (err) {
                default:
                        goto out;
                case -NFS4ERR_GRACE:
                case -NFS4ERR_DELAY:
                        nfs4_handle_exception(server, err, &exception);
                        err = 0;
                }
        } while (exception.retry);
out:
        return err;
}

static int nfs4_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *state)
{
        struct nfs_open_context *ctx;
        int ret;

        ctx = nfs4_state_find_open_context(state);
        if (IS_ERR(ctx))
                return -EAGAIN;
        ret = nfs4_do_open_expired(ctx, state);
        put_nfs_open_context(ctx);
        return ret;
}

static void nfs_finish_clear_delegation_stateid(struct nfs4_state *state)
{
        nfs_remove_bad_delegation(state->inode);
        write_seqlock(&state->seqlock);
        nfs4_stateid_copy(&state->stateid, &state->open_stateid);
        write_sequnlock(&state->seqlock);
        clear_bit(NFS_DELEGATED_STATE, &state->flags);
}

static void nfs40_clear_delegation_stateid(struct nfs4_state *state)
{
        if (rcu_access_pointer(NFS_I(state->inode)->delegation) != NULL)
                nfs_finish_clear_delegation_stateid(state);
}

static int nfs40_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *state)
{
        /* NFSv4.0 doesn't allow for delegation recovery on open expire */
        nfs40_clear_delegation_stateid(state);
        return nfs4_open_expired(sp, state);
}

#if defined(CONFIG_NFS_V4_1)
static void nfs41_check_delegation_stateid(struct nfs4_state *state)
{
        struct nfs_server *server = NFS_SERVER(state->inode);
        nfs4_stateid stateid;
        struct nfs_delegation *delegation;
        struct rpc_cred *cred;
        int status;

        /* Get the delegation credential for use by test/free_stateid */
        rcu_read_lock();
        delegation = rcu_dereference(NFS_I(state->inode)->delegation);
        if (delegation == NULL) {
                rcu_read_unlock();
                return;
        }

        nfs4_stateid_copy(&stateid, &delegation->stateid);
        cred = get_rpccred(delegation->cred);
        rcu_read_unlock();
        status = nfs41_test_stateid(server, &stateid, cred);
        trace_nfs4_test_delegation_stateid(state, NULL, status);

        if (status != NFS_OK) {
                /* Free the stateid unless the server explicitly
                 * informs us the stateid is unrecognized. */
                if (status != -NFS4ERR_BAD_STATEID)
                        nfs41_free_stateid(server, &stateid, cred);
                nfs_finish_clear_delegation_stateid(state);
        }

        put_rpccred(cred);
}

/**
 * nfs41_check_open_stateid - possibly free an open stateid
 *
 * @state: NFSv4 state for an inode
 *
 * Returns NFS_OK if recovery for this stateid is now finished.
 * Otherwise a negative NFS4ERR value is returned.
 */
static int nfs41_check_open_stateid(struct nfs4_state *state)
{
        struct nfs_server *server = NFS_SERVER(state->inode);
        nfs4_stateid *stateid = &state->open_stateid;
        struct rpc_cred *cred = state->owner->so_cred;
        int status;

        /* If a state reset has been done, test_stateid is unneeded */
        if ((test_bit(NFS_O_RDONLY_STATE, &state->flags) == 0) &&
            (test_bit(NFS_O_WRONLY_STATE, &state->flags) == 0) &&
            (test_bit(NFS_O_RDWR_STATE, &state->flags) == 0))
                return -NFS4ERR_BAD_STATEID;

        status = nfs41_test_stateid(server, stateid, cred);
        trace_nfs4_test_open_stateid(state, NULL, status);
        if (status != NFS_OK) {
                /* Free the stateid unless the server explicitly
                 * informs us the stateid is unrecognized. */
                if (status != -NFS4ERR_BAD_STATEID)
                        nfs41_free_stateid(server, stateid, cred);

                clear_bit(NFS_O_RDONLY_STATE, &state->flags);
                clear_bit(NFS_O_WRONLY_STATE, &state->flags);
                clear_bit(NFS_O_RDWR_STATE, &state->flags);
                clear_bit(NFS_OPEN_STATE, &state->flags);
        }
        return status;
}

static int nfs41_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *state)
{
        int status;

        nfs41_check_delegation_stateid(state);
        status = nfs41_check_open_stateid(state);
        if (status != NFS_OK)
                status = nfs4_open_expired(sp, state);
        return status;
}
#endif

/*
 * on an EXCLUSIVE create, the server should send back a bitmask with FATTR4-*
 * fields corresponding to attributes that were used to store the verifier.
 * Make sure we clobber those fields in the later setattr call
 */
static inline void nfs4_exclusive_attrset(struct nfs4_opendata *opendata, struct iattr *sattr)
{
        if ((opendata->o_res.attrset[1] & FATTR4_WORD1_TIME_ACCESS) &&
            !(sattr->ia_valid & ATTR_ATIME_SET))
                sattr->ia_valid |= ATTR_ATIME;

        if ((opendata->o_res.attrset[1] & FATTR4_WORD1_TIME_MODIFY) &&
            !(sattr->ia_valid & ATTR_MTIME_SET))
                sattr->ia_valid |= ATTR_MTIME;
}

static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
                fmode_t fmode,
                int flags,
                struct nfs_open_context *ctx)
{
        struct nfs4_state_owner *sp = opendata->owner;
        struct nfs_server *server = sp->so_server;
        struct dentry *dentry;
        struct nfs4_state *state;
        unsigned int seq;
        int ret;

        seq = raw_seqcount_begin(&sp->so_reclaim_seqcount);

        ret = _nfs4_proc_open(opendata);
        if (ret != 0)
                goto out;

        state = nfs4_opendata_to_nfs4_state(opendata);
        ret = PTR_ERR(state);
        if (IS_ERR(state))
                goto out;
        if (server->caps & NFS_CAP_POSIX_LOCK)
                set_bit(NFS_STATE_POSIX_LOCKS, &state->flags);

        dentry = opendata->dentry;
        if (dentry->d_inode == NULL) {
                /* FIXME: Is this d_drop() ever needed? */
                d_drop(dentry);
                dentry = d_add_unique(dentry, igrab(state->inode));
                if (dentry == NULL) {
                        dentry = opendata->dentry;
                } else if (dentry != ctx->dentry) {
                        dput(ctx->dentry);
                        ctx->dentry = dget(dentry);
                }
                nfs_set_verifier(dentry,
                                nfs_save_change_attribute(opendata->dir->d_inode));
        }

        ret = nfs4_opendata_access(sp->so_cred, opendata, state, fmode, flags);
        if (ret != 0)
                goto out;

        ctx->state = state;
        if (dentry->d_inode == state->inode) {
                nfs_inode_attach_open_context(ctx);
                if (read_seqcount_retry(&sp->so_reclaim_seqcount, seq))
                        nfs4_schedule_stateid_recovery(server, state);
        }
out:
        return ret;
}

/*
 * Returns a referenced nfs4_state
 */
static int _nfs4_do_open(struct inode *dir,
                        struct nfs_open_context *ctx,
                        int flags,
                        struct iattr *sattr,
                        struct nfs4_label *label,
                        int *opened)
{
        struct nfs4_state_owner  *sp;
        struct nfs4_state     *state = NULL;
        struct nfs_server       *server = NFS_SERVER(dir);
        struct nfs4_opendata *opendata;
        struct dentry *dentry = ctx->dentry;
        struct rpc_cred *cred = ctx->cred;
        struct nfs4_threshold **ctx_th = &ctx->mdsthreshold;
        fmode_t fmode = ctx->mode & (FMODE_READ|FMODE_WRITE|FMODE_EXEC);
        enum open_claim_type4 claim = NFS4_OPEN_CLAIM_NULL;
        struct nfs4_label *olabel = NULL;
        int status;

        /* Protect against reboot recovery conflicts */
        status = -ENOMEM;
        sp = nfs4_get_state_owner(server, cred, GFP_KERNEL);
        if (sp == NULL) {
                dprintk("nfs4_do_open: nfs4_get_state_owner failed!\n");
                goto out_err;
        }
        status = nfs4_recover_expired_lease(server);
        if (status != 0)
                goto err_put_state_owner;
        if (dentry->d_inode != NULL)
                nfs4_return_incompatible_delegation(dentry->d_inode, fmode);
        status = -ENOMEM;
        if (dentry->d_inode)
                claim = NFS4_OPEN_CLAIM_FH;
        opendata = nfs4_opendata_alloc(dentry, sp, fmode, flags, sattr,
                        label, claim, GFP_KERNEL);
        if (opendata == NULL)
                goto err_put_state_owner;

        if (label) {
                olabel = nfs4_label_alloc(server, GFP_KERNEL);
                if (IS_ERR(olabel)) {
                        status = PTR_ERR(olabel);
                        goto err_opendata_put;
                }
        }

        if (server->attr_bitmask[2] & FATTR4_WORD2_MDSTHRESHOLD) {
                if (!opendata->f_attr.mdsthreshold) {
                        opendata->f_attr.mdsthreshold = pnfs_mdsthreshold_alloc();
                        if (!opendata->f_attr.mdsthreshold)
                                goto err_free_label;
                }
                opendata->o_arg.open_bitmap = &nfs4_pnfs_open_bitmap[0];
        }
        if (dentry->d_inode != NULL)
                opendata->state = nfs4_get_open_state(dentry->d_inode, sp);

        status = _nfs4_open_and_get_state(opendata, fmode, flags, ctx);
        if (status != 0)
                goto err_free_label;
        state = ctx->state;

        if ((opendata->o_arg.open_flags & O_EXCL) &&
            (opendata->o_arg.createmode != NFS4_CREATE_GUARDED)) {
                nfs4_exclusive_attrset(opendata, sattr);

                nfs_fattr_init(opendata->o_res.f_attr);
                status = nfs4_do_setattr(state->inode, cred,
                                opendata->o_res.f_attr, sattr,
                                state, label, olabel);
                if (status == 0) {
                        nfs_setattr_update_inode(state->inode, sattr);
                        nfs_post_op_update_inode(state->inode, opendata->o_res.f_attr);
                        nfs_setsecurity(state->inode, opendata->o_res.f_attr, olabel);
                }
        }
        if (opendata->file_created)
                *opened |= FILE_CREATED;

        if (pnfs_use_threshold(ctx_th, opendata->f_attr.mdsthreshold, server)) {
                *ctx_th = opendata->f_attr.mdsthreshold;
                opendata->f_attr.mdsthreshold = NULL;
        }

        nfs4_label_free(olabel);

        nfs4_opendata_put(opendata);
        nfs4_put_state_owner(sp);
        return 0;
err_free_label:
        nfs4_label_free(olabel);
err_opendata_put:
        nfs4_opendata_put(opendata);
err_put_state_owner:
        nfs4_put_state_owner(sp);
out_err:
        return status;
}


static struct nfs4_state *nfs4_do_open(struct inode *dir,
                                        struct nfs_open_context *ctx,
                                        int flags,
                                        struct iattr *sattr,
                                        struct nfs4_label *label,
                                        int *opened)
{
        struct nfs_server *server = NFS_SERVER(dir);
        struct nfs4_exception exception = { };
        struct nfs4_state *res;
        int status;

        do {
                status = _nfs4_do_open(dir, ctx, flags, sattr, label, opened);
                res = ctx->state;
                trace_nfs4_open_file(ctx, flags, status);
                if (status == 0)
                        break;
                /* NOTE: BAD_SEQID means the server and client disagree about the
                 * book-keeping w.r.t. state-changing operations
                 * (OPEN/CLOSE/LOCK/LOCKU...)
                 * It is actually a sign of a bug on the client or on the server.
                 *
                 * If we receive a BAD_SEQID error in the particular case of
                 * doing an OPEN, we assume that nfs_increment_open_seqid() will
                 * have unhashed the old state_owner for us, and that we can
                 * therefore safely retry using a new one. We should still warn
                 * the user though...
                 */
                if (status == -NFS4ERR_BAD_SEQID) {
                        pr_warn_ratelimited("NFS: v4 server %s "
                                        " returned a bad sequence-id error!\n",
                                        NFS_SERVER(dir)->nfs_client->cl_hostname);
                        exception.retry = 1;
                        continue;
                }
                /*
                 * BAD_STATEID on OPEN means that the server cancelled our
                 * state before it received the OPEN_CONFIRM.
                 * Recover by retrying the request as per the discussion
                 * on Page 181 of RFC3530.
                 */
                if (status == -NFS4ERR_BAD_STATEID) {
                        exception.retry = 1;
                        continue;
                }
                if (status == -EAGAIN) {
                        /* We must have found a delegation */
                        exception.retry = 1;
                        continue;
                }
                if (nfs4_clear_cap_atomic_open_v1(server, status, &exception))
                        continue;
                res = ERR_PTR(nfs4_handle_exception(server,
                                        status, &exception));
        } while (exception.retry);
        return res;
}

static int _nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
                            struct nfs_fattr *fattr, struct iattr *sattr,
                            struct nfs4_state *state, struct nfs4_label *ilabel,
                            struct nfs4_label *olabel)
{
        struct nfs_server *server = NFS_SERVER(inode);
        struct nfs_setattrargs  arg = {
                .fh             = NFS_FH(inode),
                .iap            = sattr,
                .server         = server,
                .bitmask = server->attr_bitmask,
                .label          = ilabel,
        };
        struct nfs_setattrres  res = {
                .fattr          = fattr,
                .label          = olabel,
                .server         = server,
        };
        struct rpc_message msg = {
                .rpc_proc       = &nfs4_procedures[NFSPROC4_CLNT_SETATTR],
                .rpc_argp       = &arg,
                .rpc_resp       = &res,
                .rpc_cred       = cred,
        };
        unsigned long timestamp = jiffies;
        fmode_t fmode;
        bool truncate;
        int status;

        arg.bitmask = nfs4_bitmask(server, ilabel);
        if (ilabel)
                arg.bitmask = nfs4_bitmask(server, olabel);

        nfs_fattr_init(fattr);

        /* Servers should only apply open mode checks for file size changes */
        truncate = (sattr->ia_valid & ATTR_SIZE) ? true : false;
        fmode = truncate ? FMODE_WRITE : FMODE_READ;

        if (nfs4_copy_delegation_stateid(&arg.stateid, inode, fmode)) {
                /* Use that stateid */
        } else if (truncate && state != NULL) {
                struct nfs_lockowner lockowner = {
                        .l_owner = current->files,
                        .l_pid = current->tgid,
                };
                if (!nfs4_valid_open_stateid(state))
                        return -EBADF;
                if (nfs4_select_rw_stateid(&arg.stateid, state, FMODE_WRITE,
                                &lockowner) == -EIO)
                        return -EBADF;
        } else
                nfs4_stateid_copy(&arg.stateid, &zero_stateid);

        status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1);
        if (status == 0 && state != NULL)
                renew_lease(server, timestamp);
        return status;
}

static int nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
                           struct nfs_fattr *fattr, struct iattr *sattr,
                           struct nfs4_state *state, struct nfs4_label *ilabel,
                           struct nfs4_label *olabel)
{
        struct nfs_server *server = NFS_SERVER(inode);
        struct nfs4_exception exception = {
                .state = state,
                .inode = inode,
        };
        int err;
        do {
                err = _nfs4_do_setattr(inode, cred, fattr, sattr, state, ilabel, olabel);
                trace_nfs4_setattr(inode, err);
                switch (err) {
                case -NFS4ERR_OPENMODE:
                        if (!(sattr->ia_valid & ATTR_SIZE)) {
                                pr_warn_once("NFSv4: server %s is incorrectly "
                                                "applying open mode checks to "
                                                "a SETATTR that is not "
                                                "changing file size.\n",
                                                server->nfs_client->cl_hostname);
                        }
                        if (state && !(state->state & FMODE_WRITE)) {
                                err = -EBADF;
                                if (sattr->ia_valid & ATTR_OPEN)
                                        err = -EACCES;
                                goto out;
                        }
                }
                err = nfs4_handle_exception(server, err, &exception);
        } while (exception.retry);
out:
        return err;
}

struct nfs4_closedata {
        struct inode *inode;
        struct nfs4_state *state;
        struct nfs_closeargs arg;
        struct nfs_closeres res;
        struct nfs_fattr fattr;
        unsigned long timestamp;
        bool roc;
        u32 roc_barrier;
};

static void nfs4_free_closedata(void *data)
{
        struct nfs4_closedata *calldata = data;
        struct nfs4_state_owner *sp = calldata->state->owner;
        struct super_block *sb = calldata->state->inode->i_sb;

        if (calldata->roc)
                pnfs_roc_release(calldata->state->inode);
        nfs4_put_open_state(calldata->state);
        nfs_free_seqid(calldata->arg.seqid);
        nfs4_put_state_owner(sp);
        nfs_sb_deactive(sb);
        kfree(calldata);
}

static void nfs4_close_done(struct rpc_task *task, void *data)
{
        struct nfs4_closedata *calldata = data;
        struct nfs4_state *state = calldata->state;
        struct nfs_server *server = NFS_SERVER(calldata->inode);
        nfs4_stateid *res_stateid = NULL;

        dprintk("%s: begin!\n", __func__);
        if (!nfs4_sequence_done(task, &calldata->res.seq_res))
                return;
        trace_nfs4_close(state, &calldata->arg, &calldata->res, task->tk_status);
        /* hmm. we are done with the inode, and in the process of freeing
         * the state_owner. we keep this around to process errors
         */
        switch (task->tk_status) {
                case 0:
                        res_stateid = &calldata->res.stateid;
                        if (calldata->arg.fmode == 0 && calldata->roc)
                                pnfs_roc_set_barrier(state->inode,
                                                     calldata->roc_barrier);
                        renew_lease(server, calldata->timestamp);
                        break;
                case -NFS4ERR_ADMIN_REVOKED:
                case -NFS4ERR_STALE_STATEID:
                case -NFS4ERR_OLD_STATEID:
                case -NFS4ERR_BAD_STATEID:
                case -NFS4ERR_EXPIRED:
                        if (calldata->arg.fmode == 0)
                                break;
                default:
                        if (nfs4_async_handle_error(task, server, state, NULL) == -EAGAIN) {
                                rpc_restart_call_prepare(task);
                                goto out_release;
                        }
        }
        nfs_clear_open_stateid(state, res_stateid, calldata->arg.fmode);
out_release:
        nfs_release_seqid(calldata->arg.seqid);
        nfs_refresh_inode(calldata->inode, calldata->res.fattr);
        dprintk("%s: done, ret = %d!\n", __func__, task->tk_status);
}

static void nfs4_close_prepare(struct rpc_task *task, void *data)
{
        struct nfs4_closedata *calldata = data;
        struct nfs4_state *state = calldata->state;
        struct inode *inode = calldata->inode;
        bool is_rdonly, is_wronly, is_rdwr;
        int call_close = 0;

        dprintk("%s: begin!\n", __func__);
        if (nfs_wait_on_sequence(calldata->arg.seqid, task) != 0)
                goto out_wait;

        task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN_DOWNGRADE];
        spin_lock(&state->owner->so_lock);
        is_rdwr = test_bit(NFS_O_RDWR_STATE, &state->flags);
        is_rdonly = test_bit(NFS_O_RDONLY_STATE, &state->flags);
        is_wronly = test_bit(NFS_O_WRONLY_STATE, &state->flags);
        /* Calculate the change in open mode */
        calldata->arg.fmode = 0;
        if (state->n_rdwr == 0) {
                if (state->n_rdonly == 0)
                        call_close |= is_rdonly;
                else if (is_rdonly)
                        calldata->arg.fmode |= FMODE_READ;
                if (state->n_wronly == 0)
                        call_close |= is_wronly;
                else if (is_wronly)
                        calldata->arg.fmode |= FMODE_WRITE;
        } else if (is_rdwr)
                calldata->arg.fmode |= FMODE_READ|FMODE_WRITE;

        if (calldata->arg.fmode == 0)
                call_close |= is_rdwr;

        if (!nfs4_valid_open_stateid(state))
                call_close = 0;
        spin_unlock(&state->owner->so_lock);

        if (!call_close) {
                /* Note: exit _without_ calling nfs4_close_done */
                goto out_no_action;
        }

        if (calldata->arg.fmode == 0) {
                task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_CLOSE];
                if (calldata->roc &&
                    pnfs_roc_drain(inode, &calldata->roc_barrier, task)) {
                        nfs_release_seqid(calldata->arg.seqid);
                        goto out_wait;
                    }
        }

        nfs_fattr_init(calldata->res.fattr);
        calldata->timestamp = jiffies;
        if (nfs4_setup_sequence(NFS_SERVER(inode),
                                &calldata->arg.seq_args,
                                &calldata->res.seq_res,
                                task) != 0)
                nfs_release_seqid(calldata->arg.seqid);
        dprintk("%s: done!\n", __func__);
        return;
out_no_action:
        task->tk_action = NULL;
out_wait:
        nfs4_sequence_done(task, &calldata->res.seq_res);
}

static const struct rpc_call_ops nfs4_close_ops = {
        .rpc_call_prepare = nfs4_close_prepare,
        .rpc_call_done = nfs4_close_done,
        .rpc_release = nfs4_free_closedata,
};

static bool nfs4_state_has_opener(struct nfs4_state *state)
{
        /* first check existing openers */
        if (test_bit(NFS_O_RDONLY_STATE, &state->flags) != 0 &&
            state->n_rdonly != 0)
                return true;

        if (test_bit(NFS_O_WRONLY_STATE, &state->flags) != 0 &&
            state->n_wronly != 0)
                return true;

        if (test_bit(NFS_O_RDWR_STATE, &state->flags) != 0 &&
            state->n_rdwr != 0)
                return true;

        return false;
}

static bool nfs4_roc(struct inode *inode)
{
        struct nfs_inode *nfsi = NFS_I(inode);
        struct nfs_open_context *ctx;
        struct nfs4_state *state;

        spin_lock(&inode->i_lock);
        list_for_each_entry(ctx, &nfsi->open_files, list) {
                state = ctx->state;
                if (state == NULL)
                        continue;
                if (nfs4_state_has_opener(state)) {
                        spin_unlock(&inode->i_lock);
                        return false;
                }
        }
        spin_unlock(&inode->i_lock);

        if (nfs4_check_delegation(inode, FMODE_READ))
                return false;

        return pnfs_roc(inode);
}

/* 
 * It is possible for data to be read/written from a mem-mapped file 
 * after the sys_close call (which hits the vfs layer as a flush).
 * This means that we can't safely call nfsv4 close on a file until 
 * the inode is cleared. This in turn means that we are not good
 * NFSv4 citizens - we do not indicate to the server to update the file's 
 * share state even when we are done with one of the three share 
 * stateid's in the inode.
 *
 * NOTE: Caller must be holding the sp->so_owner semaphore!
 */
int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait)
{
        struct nfs_server *server = NFS_SERVER(state->inode);
        struct nfs4_closedata *calldata;
        struct nfs4_state_owner *sp = state->owner;
        struct rpc_task *task;
        struct rpc_message msg = {
                .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_CLOSE],
                .rpc_cred = state->owner->so_cred,
        };
        struct rpc_task_setup task_setup_data = {
                .rpc_client = server->client,
                .rpc_message = &msg,
                .callback_ops = &nfs4_close_ops,
                .workqueue = nfsiod_workqueue,
                .flags = RPC_TASK_ASYNC,
        };
        int status = -ENOMEM;

        nfs4_state_protect(server->nfs_client, NFS_SP4_MACH_CRED_CLEANUP,
                &task_setup_data.rpc_client, &msg);

        calldata = kzalloc(sizeof(*calldata), gfp_mask);
        if (calldata == NULL)
                goto out;
        nfs4_init_sequence(&calldata->arg.seq_args, &calldata->res.seq_res, 1);
        calldata->inode = state->inode;
        calldata->state = state;
        calldata->arg.fh = NFS_FH(state->inode);
        calldata->arg.stateid = &state->open_stateid;
        /* Serialization for the sequence id */
        calldata->arg.seqid = nfs_alloc_seqid(&state->owner->so_seqid, gfp_mask);
        if (calldata->arg.seqid == NULL)
                goto out_free_calldata;
        calldata->arg.fmode = 0;
        calldata->arg.bitmask = server->cache_consistency_bitmask;
        calldata->res.fattr = &calldata->fattr;
        calldata->res.seqid = calldata->arg.seqid;
        calldata->res.server = server;
        calldata->roc = nfs4_roc(state->inode);
        nfs_sb_active(calldata->inode->i_sb);

        msg.rpc_argp = &calldata->arg;
        msg.rpc_resp = &calldata->res;
        task_setup_data.callback_data = calldata;
        task = rpc_run_task(&task_setup_data);
        if (IS_ERR(task))
                return PTR_ERR(task);
        status = 0;
        if (wait)
                status = rpc_wait_for_completion_task(task);
        rpc_put_task(task);
        return status;
out_free_calldata:
        kfree(calldata);
out:
        nfs4_put_open_state(state);
        nfs4_put_state_owner(sp);
        return status;
}

static struct inode *
nfs4_atomic_open(struct inode *dir, struct nfs_open_context *ctx,
                int open_flags, struct iattr *attr, int *opened)
{
        struct nfs4_state *state;
        struct nfs4_label l = {0, 0, 0, NULL}, *label = NULL;

        label = nfs4_label_init_security(dir, ctx->dentry, attr, &l);

        /* Protect against concurrent sillydeletes */
        state = nfs4_do_open(dir, ctx, open_flags, attr, label, opened);

        nfs4_label_release_security(label);

        if (IS_ERR(state))
                return ERR_CAST(state);
        return state->inode;
}

static void nfs4_close_context(struct nfs_open_context *ctx, int is_sync)
{
        if (ctx->state == NULL)
                return;
        if (is_sync)
                nfs4_close_sync(ctx->state, ctx->mode);
        else
                nfs4_close_state(ctx->state, ctx->mode);
}

#define FATTR4_WORD1_NFS40_MASK (2*FATTR4_WORD1_MOUNTED_ON_FILEID - 1UL)
#define FATTR4_WORD2_NFS41_MASK (2*FATTR4_WORD2_SUPPATTR_EXCLCREAT - 1UL)
#define FATTR4_WORD2_NFS42_MASK (2*FATTR4_WORD2_SECURITY_LABEL - 1UL)

static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle)
{
        struct nfs4_server_caps_arg args = {
                .fhandle = fhandle,
        };
        struct nfs4_server_caps_res res = {};
        struct rpc_message msg = {
                .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_SERVER_CAPS],
                .rpc_argp = &args,
                .rpc_resp = &res,
        };
        int status;

        status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0);
        if (status == 0) {
                /* Sanity check the server answers */
                switch (server->nfs_client->cl_minorversion) {
                case 0:
                        res.attr_bitmask[1] &= FATTR4_WORD1_NFS40_MASK;
                        res.attr_bitmask[2] = 0;
                        break;
                case 1:
                        res.attr_bitmask[2] &= FATTR4_WORD2_NFS41_MASK;
                        break;
                case 2:
                        res.attr_bitmask[2] &= FATTR4_WORD2_NFS42_MASK;
                }
                memcpy(server->attr_bitmask, res.attr_bitmask, sizeof(server->attr_bitmask));
                server->caps &= ~(NFS_CAP_ACLS|NFS_CAP_HARDLINKS|
                                NFS_CAP_SYMLINKS|NFS_CAP_FILEID|
                                NFS_CAP_MODE|NFS_CAP_NLINK|NFS_CAP_OWNER|
                                NFS_CAP_OWNER_GROUP|NFS_CAP_ATIME|
                                NFS_CAP_CTIME|NFS_CAP_MTIME|
                                NFS_CAP_SECURITY_LABEL);
                if (res.attr_bitmask[0] & FATTR4_WORD0_ACL &&
                                res.acl_bitmask & ACL4_SUPPORT_ALLOW_ACL)
                        server->caps |= NFS_CAP_ACLS;
                if (res.has_links != 0)
                        server->caps |= NFS_CAP_HARDLINKS;
                if (res.has_symlinks != 0)
                        server->caps |= NFS_CAP_SYMLINKS;
                if (res.attr_bitmask[0] & FATTR4_WORD0_FILEID)
                        server->caps |= NFS_CAP_FILEID;
                if (res.attr_bitmask[1] & FATTR4_WORD1_MODE)
                        server->caps |= NFS_CAP_MODE;
                if (res.attr_bitmask[1] & FATTR4_WORD1_NUMLINKS)
                        server->caps |= NFS_CAP_NLINK;
                if (res.attr_bitmask[1] & FATTR4_WORD1_OWNER)
                        server->caps |= NFS_CAP_OWNER;
                if (res.attr_bitmask[1] & FATTR4_WORD1_OWNER_GROUP)
                        server->caps |= NFS_CAP_OWNER_GROUP;
                if (res.attr_bitmask[1] & FATTR4_WORD1_TIME_ACCESS)
                        server->caps |= NFS_CAP_ATIME;
                if (res.attr_bitmask[1] & FATTR4_WORD1_TIME_METADATA)
                        server->caps |= NFS_CAP_CTIME;
                if (res.attr_bitmask[1] & FATTR4_WORD1_TIME_MODIFY)
                        server->caps |= NFS_CAP_MTIME;
#ifdef CONFIG_NFS_V4_SECURITY_LABEL
                if (res.attr_bitmask[2] & FATTR4_WORD2_SECURITY_LABEL)
                        server->caps |= NFS_CAP_SECURITY_LABEL;
#endif
                memcpy(server->attr_bitmask_nl, res.attr_bitmask,
                                sizeof(server->attr_bitmask));
                server->attr_bitmask_nl[2] &= ~FATTR4_WORD2_SECURITY_LABEL;

                memcpy(server->cache_consistency_bitmask, res.attr_bitmask, sizeof(server->cache_consistency_bitmask));
                server->cache_consistency_bitmask[0] &= FATTR4_WORD0_CHANGE|FATTR4_WORD0_SIZE;
                server->cache_consistency_bitmask[1] &= FATTR4_WORD1_TIME_METADATA|FATTR4_WORD1_TIME_MODIFY;
                server->cache_consistency_bitmask[2] = 0;
                server->acl_bitmask = res.acl_bitmask;
                server->fh_expire_type = res.fh_expire_type;
        }

        return status;
}

int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle)
{
        struct nfs4_exception exception = { };
        int err;
        do {
                err = nfs4_handle_exception(server,
                                _nfs4_server_capabilities(server, fhandle),
                                &exception);
        } while (exception.retry);
        return err;
}

static int _nfs4_lookup_root(struct nfs_server *server, struct nfs_fh *fhandle,
                struct nfs_fsinfo *info)
{
        u32 bitmask[3];
        struct nfs4_lookup_root_arg args = {
                .bitmask = bitmask,
        };
        struct nfs4_lookup_res res = {
                .server = server,
                .fattr = info->fattr,
                .fh = fhandle,
        };
        struct rpc_message msg = {
                .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LOOKUP_ROOT],
                .rpc_argp = &args,
                .rpc_resp = &res,
        };

        bitmask[0] = nfs4_fattr_bitmap[0];
        bitmask[1] = nfs4_fattr_bitmap[1];
        /*
         * Process the label in the upcoming getfattr
         */
        bitmask[2] = nfs4_fattr_bitmap[2] & ~FATTR4_WORD2_SECURITY_LABEL;

        nfs_fattr_init(info->fattr);
        return nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0);
}

static int nfs4_lookup_root(struct nfs_server *server, struct nfs_fh *fhandle,
                struct nfs_fsinfo *info)
{
        struct nfs4_exception exception = { };
        int err;
        do {
                err = _nfs4_lookup_root(server, fhandle, info);
                trace_nfs4_lookup_root(server, fhandle, info->fattr, err);
                switch (err) {
                case 0:
                case -NFS4ERR_WRONGSEC:
                        goto out;
                default:
                        err = nfs4_handle_exception(server, err, &exception);
                }
        } while (exception.retry);
out:
        return err;
}

static int nfs4_lookup_root_sec(struct nfs_server *server, struct nfs_fh *fhandle,
                                struct nfs_fsinfo *info, rpc_authflavor_t flavor)
{
        struct rpc_auth_create_args auth_args = {
                .pseudoflavor = flavor,
        };
        struct rpc_auth *auth;
        int ret;

        auth = rpcauth_create(&auth_args, server->client);
        if (IS_ERR(auth)) {
                ret = -EACCES;
                goto out;
        }
        ret = nfs4_lookup_root(server, fhandle, info);
out:
        return ret;
}

/*
 * Retry pseudoroot lookup with various security flavors.  We do this when:
 *
 *   NFSv4.0: the PUTROOTFH operation returns NFS4ERR_WRONGSEC
 *   NFSv4.1: the server does not support the SECINFO_NO_NAME operation
 *
 * Returns zero on success, or a negative NFS4ERR value, or a
 * negative errno value.
 */
static int nfs4_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle,
                              struct nfs_fsinfo *info)
{
        /* Per 3530bis 15.33.5 */
        static const rpc_authflavor_t flav_array[] = {
                RPC_AUTH_GSS_KRB5P,
                RPC_AUTH_GSS_KRB5I,
                RPC_AUTH_GSS_KRB5,
                RPC_AUTH_UNIX,                  /* courtesy */
                RPC_AUTH_NULL,
        };